In real-world applications, a reinforcement learning (RL) agent should consider multiple objectives and adhere to safety guidelines. To address these considerations, we propose a constrained multi-objective RL algorithm named constrained multi-objective gradient aggregator (CoMOGA). In the field of multi-objective optimization, managing conflicts between the gradients of the multiple objectives is crucial to prevent policies from converging to local optima. It is also essential to efficiently handle safety constraints for stable training and constraint satisfaction. We address these challenges straightforwardly by treating the maximization of multiple objectives as a constrained optimization problem (COP), where the constraints are defined to improve the original objectives. Existing safety constraints are then integrated into the COP, and the policy is updated by solving the COP, which ensures the avoidance of gradient conflicts. Despite its simplicity, CoMOGA guarantees convergence to global optima in a tabular setting. Through various experiments, we have confirmed that preventing gradient conflicts is critical, and the proposed method achieves constraint satisfaction across all tasks.

As the complexity of tasks addressed through reinforcement learning (RL) increases, the definition of reward functions also has become highly complicated. We introduce an RL method aimed at simplifying the reward-shaping process through intuitive strategies. Initially, instead of a single reward function composed of various terms, we define multiple reward and cost functions within a constrained multi-objective RL (CMORL) framework. For tasks involving sequential complex movements, we segment the task into distinct stages and define multiple rewards and costs for each stage. Finally, we introduce a practical CMORL algorithm that maximizes objectives based on these rewards while satisfying constraints defined by the costs. The proposed method has been successfully demonstrated across a variety of acrobatic tasks in both simulation and real-world environments. Additionally, it has been shown to successfully perform tasks compared to existing RL and constrained RL algorithms. Our code is available at https://github.com/rllab-snu/Stage-Wise-CMORL.

Real-to-sim-to-real systems have been studied to overcome the challenges of robot policy learning in the real world by creating a virtual environment that mimics the actual workspace. However, previous studies have limitations, requiring human assistance, such as observing the workspace with a hand-held camera or manipulating objects with a hand. To solve these limitations, we propose a novel real-to-sim-to-real framework, ARIC, that performs without human help. First, ARIC observes real objects by repeatedly changing the object poses through the pre-trained robot policy via reinforcement learning. Through iterative interactions between the robot and the environment, ARIC gradually improves the accuracy of 3D object reconstruction. Next, ARIC learns task-specific robot policies in simulation using replicated objects and applies the policies to real-world scenarios without fine-tuning. We confirm that ARIC efficiently learns robotic tasks by achieving a success rate of 83.3% on average for three real-world tasks.1

Spatial relationships between objects are key to achieving well-arranged scenes. In this paper, we address the robotic rearrangement task by leveraging these relationships to reach configurations that are both well-arranged and satisfying the given language goal. We propose a hierarchical planning framework that bridges the gap between abstract language inputs and concrete robotic actions. A scene graph is central to this approach, serving as both an intermediate representation and the state for high-level planning, capturing the relationships among objects effectively and reducing planning complexity. This also enables the proposed method to handle more general language goals. To achieve this, we leverage a large language model (LLM) to convert language goals into a scene graph, which becomes the goal for high-level planning. In high-level planning, we plan transitions from the current scene graph to the goal scene graph. To integrate high-level and low-level planning, we introduce a network that generates a physical configuration of objects from a scene graph. Low-level planning then verifies the high-level plan’s feasibility, ensuring it can be executed through robotic manipulation. Through experiments, we show that the proposed method handles general language goals effectively and produces human-preferred rearrangements compared to other approaches, demonstrating its applicability on real robots without requiring sim-to-real adjustments.

Transformer-based sequence models have proven effective in offline reinforcement learning for modeling agent trajectories using large-scale datasets. However, applying these models directly to multi-agent offline reinforcement learning introduces additional challenges, especially in managing complex inter-agent dynamics that arise as multiple agents interact with both their environment and each other. To overcome these issues, we propose the context-aware multi-agent trajectory transformer (COMAT), a novel model designed for offline multi-agent reinforcement learning tasks which predicts the future trajectory of each agent by incorporating the history of adjacent agents—referred to as context—into its sequence modeling. COMAT consists of three key modules: the transformer module to process input trajectories, the context encoder to extract relevant information from adjacent agents’ histories, and the context aggregator to integrate this information into the agent’s trajectory prediction process. Built upon these modules, COMAT predicts the agents’ future trajectories and actively leverages this capability as a tool for planning, enabling the search for optimal actions in multi-agent environments. We evaluate COMAT on multi-agent MuJoCo and StarCraft Multi-Agent Challenge tasks, on which it demonstrates superior performance compared to existing baselines.

With the increase of robots navigating through crowded environments in our daily lives, the demand for designing a socially-aware navigation method considering humanrobot interaction has risen. When developing and assessing socially-aware navigation methods, pedestrian motion modeling plays a significant role. However, existing pedestrian models often struggle in complex environments and do not have the capacity to generate diverse pedestrian styles.In this paper, we propose multi-agent reinforcement learning with local coordination for individual diversity (MAC-ID), which can synthesize diverse pedestrian motions via local coordination factor (LCF). Our experiments have demonstrated that the manipulation of the LCF induces interpretable changes in pedestrian behaviors, along with a superior performance compared to existing pedestrian motion models. For evaluating socially-aware navigation methods using MAC-ID, we present a novel benchmark called BSON. It offers realistic and diverse social environments with pedestrians modeled via MAC-ID. We have trained and compared various navigation methods in BSON using a newly proposed metric called socially-aware navigation score (SNS). Through BSON, users can evaluate their socially-aware navigation methods and compare them to baselines.

This paper tackles a localization problem in large-scale indoor environments with wayfinding maps. A wayfinding map abstractly portrays the environment, and humans can localize themselves based on the map. However, when it comes to using it for robot localization, large geometrical discrepancies between the wayfinding map and the real world make it hard to use conventional localization methods. Our objective is to estimate a robot pose within a wayfinding map, utilizing RGB images from perspective cameras. We introduce two different imagination modules which are inspired by how humans can comprehend and interpret their surroundings for localization purposes. These modules jointly learn how to effectively observe the first-person-view (FPV) world to interpret bird-eye-view (BEV) maps. Providing explicit guidance to the two imagination modules significantly improves the precision of the localization system. We demonstrate the effectiveness of the proposed approach using real-world datasets, which are collected from various large-scale crowded indoor environments. The experimental results show that, in 85% of scenarios, the proposed localization system can estimate its pose within 3m in large indoor spaces. Project Site: https://rllab-snu.github.io/projects/WayIL/

We propose a novel unsupervised method for motion-based 3D part decomposition of articulated objects using a single monocular video of a dynamic scene. In contrast to existing unsupervised methods relying on optical flow or tracking techniques, our approach addresses this problem without additional information by leveraging Gaussian splatting techniques. We generate a series of Gaussians from a monocular video and analyze their relationships to decompose the dynamic scene into motion-based parts. To decompose dynamic scenes consisting of articulated objects, we design an articulated deformation field suitable for the movement of articulated objects. And to effectively understand the relationships of Gaussians of different shapes, we propose a 3D reconstruction loss using 3D occupied voxel maps generated from the Gaussians. Experimental results demonstrate that our method outperforms existing approaches in terms of 3D part decomposition for articulated objects. More demos and code are available at https://choonsik93.github.io/artnerf/.

In this paper, we introduce a new method that first utilizes 3D Gaussian splatting in street-level localization problem. Robust localization with street-level real-world images such as street view is a major issue for autonomous vehicle, augmented reality (AR) navigation, and outdoor mobile robots. The objective is to determine the position and orientation of a query image that matches a street view database composed of RGB images. However, given the limited information available in the street view images, accurately determining the location solely based on this data presents a significant challenge. To address this challenge, we propose a novel method called renderable street view map-based localization (RSM-Loc). This approach enhances the localization process by augmenting 2D street view images into a renderable 3D map using 3D Gaussian splatting, to resolve street-level localization problems. Upon receiving a query RGB image without geometry information, the proposed method renders 2D images from a pre-made renderable map and compares image pose similarities between the rendered images and the query image. Through iterations of this process, the proposed method eventually estimates the pose of the given query image. The experimental results demonstrate that RSM-Loc outperforms the baselines with neural-field-based localization. Additionally, we conduct deep analysis on the proposed method to show that our method can serve as a new concept for the street-level localization problem.

The bin packing problem (BPP) is a challenging combinatorial optimization problem with a number of practical applications. This paper focuses on online 3D-BPP, where the packer makes immediate decisions for a loading position as items continually arrive. We propose a novel reinforcement learning algorithm, GREViT, which utilizes a vision transformer to tackle online 3D-BPP for the first time. By introducing the gradual receptive expansion technique, GREViT overcomes the limitations inherent in learning-based methods that only excel in their trained bins. As a result, GREViT surpasses existing BPP algorithms in packing ratio across various bin sizes. The effectiveness of GREViT in real-world scenarios is validated by its successful demonstrations using a real robot for solving 3D-BPP. The attached video demonstrates GREViT undertaking 3D-BPP in both simulated and real-world environments.

We propose a novel visual localization and navigation framework for real-world environments directly integrating observed visual information into the bird-eye-view map. While the renderable neural radiance map (RNR-Map) [1] shows considerable promise in simulated settings, its deployment in real-world scenarios poses undiscovered challenges. RNR-Map utilizes projections of multiple vectors into a single latent code, resulting in information loss under suboptimal conditions. To address such issues, our enhanced RNR-Map for real-world robots, RNR-Map++, incorporates strategies to mitigate information loss, such as a weighted map and positional encoding. For robust real-time localization, we integrate a particle filter into the correlation-based localization framework using RNR-Map++ without a rendering procedure. Consequently, we establish a real-world robot system for visual navigation utilizing RNR-Map++, which we call "RNR-Nav." Experimental results demonstrate that the proposed methods significantly enhance rendering quality and localization robustness compared to previous approaches. In real-world navigation tasks, RNR-Nav achieves a success rate of 84.4%, marking a 68.8% enhancement over the methods of the original RNR-Map paper.

In the realm of autonomous agents, ensuring safety and reliability in complex and dynamic environments remains a paramount challenge. Safe reinforcement learning addresses these concerns by introducing safety constraints, but still faces challenges in navigating intricate environments such as complex driving situations. To overcome these challenges, we present the safe constraint reward (Safe CoR) framework, a novel method that utilizes two types of expert demonstrations—reward expert demonstrations focusing on performance optimization and safe expert demonstrations prioritizing safety. By exploiting a constraint reward (CoR), our framework guides the agent to balance performance goals of reward sum with safety constraints. We test the proposed framework in diverse environments, including the safety gym, metadrive, and the real-world Jackal platform. Our proposed framework improves algorithm performance by 39% and reduces constraint violations by 88% on the real-world Jackal platform, highlighting its effectiveness. Through this innovative approach, we expect significant advancements in real-world performance, leading to transformative effects in the realm of safe and reliable autonomous agents.

Training agents that are robust to environmental changes remains a significant challenge in deep reinforcement learning (RL). Unsupervised environment design (UED) has recently emerged to address this issue by generating a set of training environments tailored to the agent's capabilities. While prior works demonstrate that UED has the potential to learn a robust policy, their performance is constrained by the capabilities of the environment generation. To this end, we propose a novel UED algorithm, adversarial environment design via regret-guided diffusion models (ADD). The proposed method guides the diffusion-based environment generator with the regret of the agent to produce environments that the agent finds challenging but conducive to further improvement. By exploiting the representation power of diffusion models, ADD can directly generate adversarial environments while maintaining the diversity of training environments, enabling the agent to effectively learn a robust policy. Our experimental results demonstrate that the proposed method successfully generates an instructive curriculum of environments, outperforming UED baselines in zero-shot generalization across novel, out-of-distribution environments.

The field of risk-constrained reinforcement learning (RCRL) has been developed to effectively reduce the likelihood of worst-case scenarios by explicitly handling risk-measure-based constraints. However, the nonlinearity of risk measures makes it challenging to achieve convergence and optimality. To overcome the difficulties posed by the nonlinearity, we propose a spectral risk measure-constrained RL algorithm, spectral-risk-constrained policy optimization (SRCPO), a bilevel optimization approach that utilizes the duality of spectral risk measures. In the bilevel optimization structure, the outer problem involves optimizing dual variables derived from the risk measures, while the inner problem involves finding an optimal policy given these dual variables. The proposed method, to the best of our knowledge, is the first to guarantee convergence to an optimum in the tabular setting. Furthermore, the proposed method has been evaluated on continuous control tasks and showed the best performance among other RCRL algorithms satisfying the constraints. Our code is available at https://github.com/rllab-snu/Spectral-Risk-Constrained-RL.

The main challenge in vision-and-language navigation (VLN) is how to understand natural-language instructions in an unseen environment. The main limitation of conventional VLN algorithms is that if an action is mistaken, the agent fails to follow the instructions or explores unnecessary regions, leading the agent to an irrecoverable path. To tackle this problem, we propose Meta-Explore, a hierarchical navigation method deploying an exploitation policy to correct misled recent actions. We show that an exploitation policy, which moves the agent toward a well-chosen local goal among unvisited but observable states, outperforms a method which moves the agent to a previously visited state. We also highlight the demand for imagining regretful explorations with semantically meaningful clues. The key to our approach is understanding the object placements around the agent in spectral-domain. Specifically, we present a novel visual representation, called scene object spectrum (SOS), which performs category-wise 2D Fourier transform of detected objects. Combining exploitation policy and SOS features, the agent can correct its path by choosing a promising local goal. We evaluate our method in three VLN benchmarks: R2R, SOON, and REVERIE. Meta-Explore outper-forms other baselines and shows significant generalization performance. In addition, local goal search using the proposed spectral-domain SOS features significantly improves the success rate by 17.1% and SPL by 20. 6% against the state-of-the-art method of the SOON benchmark. Project page: https://rllab-snu.github.io/projects/Meta-Explore/doc.html

We propose a novel type of map for visual navigation, a renderable neural radiance map (RNR-Map), which is designed to contain the overall visual information of a 3D environment. The RNR-Map has a grid form and consists of latent codes at each pixel. These latent codes are embedded from image observations, and can be converted to the neural radiance field which enables image rendering given a camera pose. The recorded latent codes implicitly contain visual information about the environment, which makes the RNR-Map visually descriptive. This visual information in RNR-Map can be a useful guideline for visual localization and navigation. We develop localization and navigation frameworks that can effectively utilize the RNR-Map. We evaluate the proposed frameworks on camera tracking, visual localization, and image-goal navigation. Experimental results show that the RNR-Map-based localization framework can find the target location based on a single query image with fast speed and competitive accuracy compared to other baselines. Also, this localization framework is robust to environmental changes, and even finds the most visually similar places when a query image from a different environment is given. The proposed navigation framework outperforms the existing image-goal navigation methods in difficult scenarios, under odometry and actuation noises. The navigation framework shows 65.7% success rate in curved scenarios of the NRNS [21] dataset, which is an improvement of 18.6% over the current state-of-the-art. Project page: https://rllab-snu.github.io/projects/RNR-Map/

In this paper, we propose a signed distance field (SDF)-based deep Q-learning framework for multi-object re-arrangement. Our method learns to rearrange objects with non-prehensile manipulation, e.g., pushing, in unstructured environments. To reliably estimate Q-values in various scenes, we train the Q-network using an SDF-based scene graph as the state-goal representation. To this end, we introduce SDFGCN, a scalable Q-network structure which can estimate Q-values from a set of SDF images satisfying permutation invariance by using graph convolutional networks. In contrast to grasping-based rearrangement methods that rely on the performance of grasp predictive models for perception and movement, our approach enables rearrangements on unseen objects, including hard-to-grasp objects. Moreover, our method does not require any expert demonstrations. We observe that SDFGCN is capable of unseen objects in challenging configurations, both in the simulation and the real world.

Designing a socially-aware navigation method for crowded environments has become a critical issue in robotics. In order to perform navigation in a crowded environment without causing discomfort to nearby pedestrians, it is necessary to design a global planner that is able to consider both human-robot interaction (HRI) and prediction of future states. In this paper, we propose a socially-aware global planner called SCAN, which is a global planner that generates appropriate local goals considering HRI and prediction of future states. Our method simulates future states considering the effects of the robot's actions on the future intentions of pedestrians using Monte Carlo tree search (MCTS), which estimates the quality of local goals. For fast simulation, we execute pedestrian motion prediction using Y-net and future state simulation using MCTS in parallel. Neural networks are only used in Y-net and not in MCTS, which enables fast simulation and prediction of a long horizon of future states. We evaluate the proposed method based on the proposed socially-aware navigation metric using realistic pedestrian simulation and real-world experiments. The results show that the proposed method outperforms existing methods significantly, indicating the importance of considering human-robot interaction for socially-aware navigation.

In this paper, we perform an object rearrangement task for target retrieval in an environment with a confined space and limited observation directions. The agent must create a collision-free path to bring out the target object by relocating the surrounding objects using the prehensile action, i.e., pick-and-place. Object rearrangement in a confined space is a non-monotone problem, and finding a valid plan within a reasonable time is challenging. We propose a novel algorithm that divides the target retrieval task, which requires a long sequence of actions, into sequential sub-problems and explores each solution through Monte Carlo tree search (MCTS). In the experiment, we verify that the proposed algorithm can find safe rearrangement plans with various objects efficiently compared to the existing planning methods. Furthermore, we show that the proposed method can be transferred to a real robot experiment without additional training.

Satisfying safety constraints in reinforcement learning (RL) is an important issue, especially in real-world applications. Many studies have approached safe RL with the Lagrangian method, which introduces dual variables. However, applying a trained policy with the optimal dual variable to a new environment can be hazardous since the optimal value of the dual variable, which represents a level of safety, depends on the environmental setting. To this end, we propose a new framework, dual variable actor-critic (DVAC), that solves the safe RL problem by simultaneously training a single policy over different safety levels. We introduce a universal policy and universal Q-function, which have a dual variable as an argument. Then, we extend the soft actor-critic so that the universal policy is guaranteed to converge to the Pareto optimal policy sets. We evaluate the proposed method in simulation and real-world environments. The universal policy learned with the proposed method ranges from extremely safe to high performance according to the dual variables, and is nearly Pareto optimal compared to policies learned with the baseline methods. In addition, the agent is able to adapt to environments with unseen state distributions without additional training by identifying a suitable dual variable using the proposed method.

Addressing decision-making problems using sequence modeling to predict future trajectories shows promising results in recent years. In this paper, we take a step further to leverage the sequence predictive method in wider areas such as long-term planning, vision-based control, and multi-task decision-making. To this end, we propose a method to utilize a diffusion-based generative sequence model to plan a series of milestones in a latent space and to have an agent to follow the milestones to accomplish a given task. The proposed method can learn control-relevant, low-dimensional latent representations of milestones, which makes it possible to efficiently perform long-term planning and vision-based control. Furthermore, our approach exploits generation flexibility of the diffusion model, which makes it possible to plan diverse trajectories for multi-task decision-making. We demonstrate the proposed method across offline reinforcement learning (RL) benchmarks and an visual manipulation environment. The results show that our approach outperforms offline RL methods in solving long-horizon, sparse-reward tasks and multi-task problems, while also achieving the state-of-the-art performance on the most challenging vision-based manipulation benchmark.

Reinforcement learning from human feedback (RLHF) alleviates the problem of designing a task-specific reward function in reinforcement learning by learning it from human preference. However, existing RLHF models are considered inefficient as they produce only a single preference data from each human feedback. To tackle this problem, we propose a novel RLHF framework called SeqRank, that uses sequential preference ranking to enhance the feedback efficiency. Our method samples trajectories in a sequential manner by iteratively selecting a defender from the set of previously chosen trajectories $\mathcal{K}$ and a challenger from the set of unchosen trajectories $\mathcal{U}\setminus\mathcal{K}$, where $\mathcal{U}$ is the replay buffer. We propose two trajectory comparison methods with different defender sampling strategies: (1) sequential pairwise comparison that selects the most recent trajectory and (2) root pairwise comparison that selects the most preferred trajectory from $\mathcal{K}$. We construct a data structure and rank trajectories by preference to augment additional queries. The proposed method results in at least 39.2% higher average feedback efficiency than the baseline and also achieves a balance between feedback efficiency and data dependency. We examine the convergence of the empirical risk and the generalization bound of the reward model with Rademacher complexity. While both trajectory comparison methods outperform conventional pairwise comparison, root pairwise comparison improves the average reward in locomotion tasks and the average success rate in manipulation tasks by 29.0% and 25.0%, respectively. The source code and the videos are provided in the supplementary material.

In safety-critical robotic tasks, potential failures must be reduced, and multiple constraints must be met, such as avoiding collisions, limiting energy consumption, and maintaining balance. Thus, applying safe reinforcement learning (RL) in such robotic tasks requires to handle multiple constraints and use risk-averse constraints rather than risk-neutral constraints. To this end, we propose a trust region-based safe RL algorithm for multiple constraints called a safe distributional actor-critic (SDAC). Our main contributions are as follows: 1) introducing a gradient integration method to manage infeasibility issues in multi-constrained problems, ensuring theoretical convergence, and 2) developing a TD($\lambda$) target distribution to estimate risk-averse constraints with low biases. We evaluate SDAC through extensive experiments involving multi- and single-constrained robotic tasks. While maintaining high scores, SDAC shows 1.93 times fewer steps to satisfy all constraints in multi-constrained tasks and 1.78 times fewer constraint violations in single-constrained tasks compared to safe RL baselines. Code is available at: https://github.com/rllab-snu/Safe-Distributional-Actor-Critic.

We propose a dual-domain generative model to estimate a texture map from a single image for colorizing a 3D human model. When estimating a texture map, a single image is insufficient as it reveals only one facet of a 3D object. To provide sufficient information for estimating a complete texture map, the proposed model simultaneously generates multi-view hallucinations in the image domain and an estimated texture map in the texture domain. During the generating process, each domain generator exchanges features to the other by a flow-based local attention mechanism. In this manner, the proposed model can estimate a texture map utilizing abundant multi-view image features from which multiview hallucinations are generated. As a result, the estimated texture map contains consistent colors and patterns over the entire region. Experiments show the superiority of our model for estimating a directly render-able texture map, which is applicable to 3D animation rendering. Furthermore, our model also improves an overall generation quality in the image domain for pose and viewpoint transfer tasks.

This paper emphasizes the importance of a robot's ability to refer to its task history, especially when it exe-cutes a series of pick-and-place manipulations by following language instructions given one by one. The advantage of referring to the manipulation history can be categorized into two folds: (1) the language instructions omitting details but using expressions referring to the past can be interpreted, and (2) the visual information of objects occluded by previous manipulations can be inferred. For this, we introduce a history-dependent manipulation task which objective is to visually ground a series of language instructions for proper pick-and-place manipulations by referring to the past. We also suggest a relevant dataset and model which can be a baseline, and show that our model trained with the proposed dataset can also be applied to the real world based on the CycleGAN. Our dataset and code are publicly available on the project website: https://sites.google.com/view/history-dependent-manipulation.

In this paper, we present a novel autonomous driving framework, called a road graph and image attention network (RIANet), which computes the attention scores of objects in the image using the road graph feature. The process of the proposed method is as follows: First, the feature encoder module encodes the road graph, image, and additional features of the scene. The attention network module then incorporates the encoded features and computes the scene context feature via the attention mechanism. Finally, the low-level controller mod-ule drives the ego-vehicle based on the scene context feature. In the experiments, we use an urban scene driving simulator named CARLA to train and test the proposed method. The results show that the proposed method outperforms existing autonomous driving methods.

In the lateral access environment, the robot be-havior should be planned considering surrounding objects and obstacles because object observation directions and approach angles are limited. To safely retrieve a partially occluded target object in these environments, we have to relocate objects using prehensile actions to create a collision-free path for the target. We propose a learning-based method for object rearrangement planning applicable to objects of various types and sizes in the lateral environment. We plan the optimal rearrangement sequence by considering both collisions and approach angles at which objects can be grasped. The proposed method finds the grasping order through Monte Carlo tree search, significantly reducing the tree search cost using point cloud states. In the experiment, the proposed method shows the best and most stable performance in various scenarios compared to the existing TAMP methods. In addition, we confirm that the proposed method trained in simulation can be easily applied to a real robot without additional fine-tuning, showing the robustness of the proposed method.

Satisfying safety constraints is the top priority in safe reinforcement learning (RL). However, without proper exploration, an overly conservative policy such as freezing at the same position can be generated. To this end, we utilize maximum entropy RL methods for exploration. In particular, an RL method with Tsallis entropy maximization, called Tsallis actor-critic (TAC), is used to synthesize policies which can explore with more promising actions. In this paper, we propose a Tsallis entropy-regularized safe RL method for safer exploration, called SafeTAC. For more expressiveness, we extend the TAC to use a Gaussian mixture model policy, which improves the safety performance. To stabilize the training process, the retrace estimators for safety critics are formulated, and a safe policy update rule using a trust region method is proposed.

In reinforcement learning (RL), exploration is essential to achieve a globally optimal policy but unconstrained exploration can cause damages to robots and nearby people. To handle this safety issue in exploration, safe RL has been proposed to keep the agent under the specified safety constraints while maximizing cumulative rewards. This paper introduces a new safe RL method which can be applied to robots to operate under the safety constraints while learning. The key component of the proposed method is the safeguard module. The safeguard predicts the constraints in the near future and corrects actions such that the predicted constraints are not violated. Since actions are safely modified by the safeguard during exploration and policies are trained to imitate the corrected actions, the agent can safely explore. Additionally, the safeguard is sample efficient as it does not require long horizontal trajectories for training, so constraints can be satisfied within short time steps. The proposed method is extensively evaluated in simulation and experiments using a real robot. The results show that the proposed method achieves the best performance while satisfying safety constraints with minimal interaction with environments in all experiments.

Designing or learning an autonomous driving policy is undoubtedly a challenging task as the policy has to maintain its safety in all corner cases. In order to secure safety in autonomous driving, the ability to detect hazardous situations, which can be seen as an out-of-distribution (OOD) detection problem, becomes crucial. However, conventional datasets often only contain expert driving demonstrations, although some non-expert or uncommon driving behavior data are needed to implement a safety guaranteed autonomous driving platform. To this end, we present a dataset called the R3 Driving Dataset, composed of driving data with different qualities. The dataset categorizes abnormal driving behaviors into eight categories and 369 different detailed situations. The situations include dangerous lane changes and near-collision situations. To further enlighten how these abnormal driving behaviors can be detected, we utilize different uncertainty estimation and anomaly detection methods for the proposed dataset. From the results of the proposed experiment, it can be inferred that by using both uncertainty estimation and anomaly detection, most of the abnormal cases in the proposed dataset can be discriminated. https://rllab-snu.github.io/projects/R3-Driving-Dataset/doc.html

We present a novel graph-structured memory for visual navigation, called visual graph memory (VGM), which consists of unsupervised image representations obtained from navigation history. The proposed VGM is constructed incrementally based on the similarities among the unsupervised representations of observed images, and these representations are learned from an unlabeled image dataset. We also propose a navigation framework that can utilize the proposed VGM to tackle visual navigation problems. By incorporating a graph convolutional network and the attention mechanism, the proposed agent refers to the VGM to navigate the environment while simultaneously building the VGM. Using the VGM, the agent can embed its navigation history and other useful task-related information. We validate our approach on the visual navigation tasks using the Habitat simulator with the Gibson dataset, which provides a photo-realistic simulation environment. The extensive experimental results show that the proposed navigation agent with VGM surpasses the state-of-the-art approaches on image-goal navigation tasks. Project Page: https://sites.google.com/view/iccv2021vgm

We propose a novel autonomous driving frame-work that leverages graph-based features of roads, such as road positions and connections. The proposed method is divided into two parts: a low-level controller which follows the trajectory calculated by a graph-based path planner, and a high-level controller which determines the speed of the vehicle to follow the traffic flow. The high-level controller uses a road graphical neural network (Road-GNN), which encodes a road graph into latent features to perceive the surrounding environment. We use a 3D driving simulator to test the performance of Road-GNN, which is implemented based on the satellite image data of 30 roundabout intersections. To show that the proposed method can be generalized to various road environments, the proposed method is tested using roundabouts which are different from the training set. In the experiment, the proposed method successfully trains the agent and drives an ego-vehicle through various roundabout environments. The results show that the graph-based method is effective for autonomous driving.

Much progress has been made for non-rigid structure from motion (NRSfM) during the last two decades, which made it possible to provide reasonable solutions for synthetically-created benchmark data. In order to utilize these NRSfM techniques in more realistic situations, however, we are now facing two important problems that must be solved: First, general scenes contain complex deformations as well as multiple objects, which violates the usual assumptions of previous NRSfM proposals. Second, there are many unreconstructable regions in the video, either because of the discontinued tracks of 2D trajectories or those regions static towards the camera, which require careful manipulations. In this paper, we show that a consensus-based reconstruction framework can handle these issues effectively. Even though the entire scene is complex, its parts usually have simpler deformations, and even though there are some unreconstructable parts, they can be weeded out to reduce their harmful effect on the entire reconstruction. The main difficulty of this approach lies in identifying appropriate parts, however, it can be effectively avoided by sampling parts stochastically and then aggregate their reconstructions afterwards. Experimental results show that the proposed method renews the state-of-the-art for popular benchmark data under much harsher environments, i.e., narrow camera view ranges, and it can reconstruct video-based real-world data effectively for as many areas as it can without an elaborated user input.

In this paper, we tackle the problem of 6-DoF grasp detection which is crucial for robot grasping in cluttered real-world scenes. Unlike existing approaches which synthesize 6-DoF grasp data sets and train grasp quality networks with input grasp representations based on point clouds, we rather take a novel hierarchical approach which does not use any 6-DoF grasp data. We cast the 6-DoF grasp detection problem as a robot arm approaching direction selection problem using the existing 4-DoF grasp detection algorithm, by exploiting a fully convolutional grasp quality network for evaluating the quality of an approaching direction. To select the best approaching direction with the highest grasp quality, we propose an approaching direction selection method which leverages a geometry-based prior and a derivative-free optimization method. Specifically, we optimize the direction iteratively using the cross entropy method with initial samples of surface normal directions. Our algorithm efficiently finds diverse 6-DoF grasps by the novel way of evaluating and optimizing approaching directions. We validate that the proposed method outperforms other selection methods in scenarios with cluttered objects in a physics-based simulator. Finally, we show that our method outperforms the state-of-the-art grasp detection method in real-world experiments with robots.

This paper proposes a multiple stakeholder perspective model (MSPM) which predicts the future pedestrian trajectory observed from vehicle's point of view. For the vehicle-pedestrian interaction, the estimation of the pedestrian's intention is a key factor. However, even if this interaction is commonly initiated by both the human (pedestrian) and the agent (driver), current research focuses on developing a neural network trained by the data from driver's perspective only. In this paper, we suggest a multiple stakeholder perspective model (MSPM) and apply this model for pedestrian intention prediction. The model combines the driver (stakeholder 1) and pedestrian (stakeholder 2) by separating the information based on the perspective. The dataset from pedestrian's perspective have been collected from the virtual reality experiment, and a network that can reflect perspectives of both pedestrian and driver is proposed. Our model achieves the best performance in the existing pedestrian intention dataset, while reducing the trajectory prediction error by average of 4.48% in the short-term (0.5s) and middle-term (1.0s) prediction, and 11.14% in the long-term prediction (1.5s) compared to the previous state-of-the-art.

In this paper, we propose a novel contextual bandit algorithm that employs a neural network as a reward estimator and utilizes Shannon entropy regularization to encourage exploration, which is called Shannon entropy regularized neural contextual bandits (SERN). In many learning-based algorithms for robotic grasping, the lack of the real-world data hampers the generalization performance of a model and makes it difficult to apply a trained model to real-world problems. To handle this issue, the proposed method utilizes the benefit of an online learning. The proposed method trains a neural network to predict the success probability of a given grasp pose based on a depth image, which is called a grasp quality. We theoretically show that the SERN has a no regret property. We empirically demonstrate that the SERN outperforms ε-greedy in terms of sample efficiency.

In this paper, we consider autonomous driving of a vehicle using imitation learning. Generative adversarial imitation learning (GAIL) is a widely used algorithm for imitation learning. This algorithm leverages positive demonstrations to imitate the behavior of an expert. In this paper, we propose a novel method, called mixed generative adversarial imitation learning (MixGAIL), which incorporates both of expert demonstrations and negative demonstrations, such as vehicle collisions. To this end, the proposed method utilizes an occupancy measure and a constraint function. The occupancy measure is used to follow expert demonstrations and provides a positive feedback. On the other hand, the constraint function is used for negative demonstrations to assert a negative feedback. Experimental results show that the proposed algorithm converges faster than the other baseline methods. Also, hardware experiments using a real-world RC car shows an outstanding performance and faster convergence compared with existing methods.

In this paper, we consider stochastic multi-armed bandits (MABs) with heavy-tailed rewards, whose p-th moment is bounded by a constant nu_p for 1

Deep networks consume a large amount of memory by their nature. A natural question arises can we reduce that memory requirement whilst maintaining performance. In particular, in this work we address the problem of memory efficient learning for multiple tasks. To this end, we propose a novel network architecture producing multiple networks of different configurations, termed deep virtual networks (DVNs), for different tasks. Each DVN is specialized for a single task and structured hierarchically. The hierarchical structure, which contains multiple levels of hierarchy corresponding to different numbers of parameters, enables multiple inference for different memory budgets. The building block of a deep virtual network is based on a disjoint collection of parameters of a network, which we call a unit. The lowest level of hierarchy in a deep virtual network is a unit, and higher levels of hierarchy contain lower levels' units and other additional units. Given a budget on the number of parameters, a different level of a deep virtual network can be chosen to perform the task. A unit can be shared by different DVNs, allowing multiple DVNs in a single network. In addition, shared units provide assistance to the target task with additional knowledge learned from another tasks. This cooperative configuration of DVNs makes it possible to handle different tasks in a memory-aware manner. Our experiments show that the proposed method outperforms existing approaches for multiple tasks. Notably, ours is more efficient than others as it allows memory-aware inference for all tasks.

In this work, we consider the problem of instance-wise dynamic network model selection for multi-task learning. To this end, we propose an efficient approach to exploit a compact but accurate model in a backbone architecture for each instance of all tasks. The proposed method consists of an estimator and a selector. The estimator is based on a backbone architecture and structured hierarchically. It can produce multiple different network models of different configurations in a hierarchical structure. The selector chooses a model dynamically from a pool of candidate models given an input instance. The selector is a relatively small-size network consisting of a few layers, which estimates a probability distribution over the candidate models when an input instance of a task is given. Both estimator and selector are jointly trained in a unified learning framework in conjunction with a sampling-based learning strategy, without additional computation steps. We demonstrate the proposed approach for several image classification tasks compared to existing approaches performing model selection or learning multiple tasks. Experimental results show that our approach gives not only outstanding performance compared to other competitors but also the versatility to perform instance-wise model selection for multiple tasks.

In this paper, we propose 3D unsupervised reconstruction networks (3D-URN), which reconstruct the 3D structures of instances in a given object category from their 2D feature points under an orthographic camera model. 3D-URN consists of a 3D shape reconstructor and a rotation estimator, which are trained in a fully-unsupervised manner incorporating the proposed unsupervised loss functions. The role of the 3D shape reconstructor is to reconstruct the 3D shape of an instance from its 2D feature points, and the rotation estimator infers the camera pose. After training, 3D-URN can infer the 3D structure of an unseen instance in the same category, which is not possible in the conventional schemes of non-rigid structure from motion and structure from category. The experimental result shows the state-of-the-art performance, which demonstrates the effectiveness of the proposed method.

In this paper, we propose a novel distributional reinforcement learning (RL) method which models the distribution of the sum of rewards using a mixture density network. Recently, it has been shown that modeling the randomness of the return distribution leads to better performance in Atari games and control tasks. Despite the success of the prior work, it has limitations which come from the use of a discrete distribution. First, it needs a projection step and softmax parametrization for the distribution, since it minimizes the KL divergence loss. Secondly, its performance depends on discretization hyperparameters such as the number of atoms and bounds of the support which require domain knowledge. We mitigate these problems with the proposed parameterization, a mixture of Gaussians. Furthermore, we propose a new distance metric called the Jensen-Tsallis distance, which allows the computation of the distance between two mixtures of Gaussians in a closed form. We have conducted various experiments to validate the proposed method, including Atari games and autonomous vehicle driving.

Autonomous driving is a challenging problem because the autonomous vehicle must understand complex and dynamic environment. This understanding consists of predicting future behavior of nearby vehicles and recognizing predefined rules. It is observed that not all rules have equivalent values, and the priority of the rules may change depending on the situation or the driver's driving style. In this work, we jointly reason both a future trajectories of vehicles and degree of satisfaction of each rule in the deep learning framework. Joint reasoning allows modeling interactions between vehicles, and leads to better prediction results. A rule is represented as a signal temporal logic (STL) formula, and a robustness slackness, a margin to the satisfaction of the rule, is predicted for the both autonomous and other vehicle, in addition to future trajectories. Learned robustness slackness decides which rule should be prioritized for the given situation for the autonomous vehicle, and filter out non-valid predicted trajectories for surrounding vehicles. The predicted information from the deep learning framework is used in model predictive control (MPC), which allows the autonomous vehicle navigate efficiently and safely. We test the feasibility of our approach in publicly available NGSIM datasets. Proposed method shows a driving style similar to the human one and considers the safety related to the rules through the future prediction of the surrounding vehicles.

Recent advances of actor-critic methods in deep reinforcement learning have enabled performing several continuous control problems. However, existing actor-critic algorithms require a large number of parameters to model policy and value functions where it can lead to overfitting issue and is difficult to tune hyperparameter. In this paper, we introduce a new off-policy actor-critic algorithm, which can reduce a significant number of parameters compared to existing actorcritic algorithms without any performance loss. The proposed method replaces the actor network with a set of action particles that employ few parameters. Then, the policy distribution is represented using state action value network with action particles. During the learning phase, to improve the performance of policy distribution, the location of action particles is updated to maximize state action values. To enhance the exploration and stable convergence, we add perturbation to action particles during training. In the experiment, we validate the proposed method in MuJoCo environments and empirically show that our method shows similar or better performance than the state-of-the-art actor-critic method with a smaller number of parameters. The experimental video can be found at http: //rllab.snu.ac.kr/multimedia.

In this paper, we consider the problem of estimating the head pose and body orientation of a person from a low-resolution image. Under this setting, it is difficult to reliably extract facial features or detect body parts. We propose a convolutional random projection forest (CRPforest) algorithm for these tasks. A convolutional random projection network (CRPnet) is used at each node of the forest. It maps an input image to a high-dimensional feature space using a rich filter bank. The filter bank is designed to generate sparse responses so that they can be efficiently computed by compressive sensing. A sparse random projection matrix can capture most essential information contained in the filter bank without using all the filters in it. Therefore, the CRPnet is fast, e.g., it requires to process an image of pixels, due to the small number of convolutions (e.g., 0.01 percent of a layer of a neural network) at the expense of less than 2 percent accuracy. The overall forest estimates head and body pose well on benchmark datasets, e.g., over 98 percent on the HIIT dataset, while requiring without using a GPU. Extensive experiments on challenging datasets show that the proposed algorithm performs favorably against the state-of-the-art methods in low-resolution images with noise, occlusion, and motion blur.

In this paper, we focus on the problem of learning from demonstration (LfD) where demonstrations with different proficiencies are provided without labeling. To this end, we model multiple policies with different qualities as correlated Gaussian processes and present a leverage optimization method that estimates the leverage of each policy where the difference between two leverages defines the correlation between the corresponding policies. To recover a single policy function of an expert, we present a sparsity constraint on the leverage parameters. We first show that the proposed leverage optimization method can recover the correlations between sensory fields where the fields are realized from correlated Gaussian processes and sensor measurements are collected from the fields. Furthermore, we applied the proposed method to autonomous driving experiments, where demonstrations are collected from three different driving modes. While the driving policies are not realized from correlated processes, the proposed method assigns reasonable leverages to the driving demonstrations. The estimated driving policy of an expert, which incorporates the optimized leverages, outperforms previous LfD methods in terms of both safety and driving quality.

Recently, there have been increasing demands to construct compact deep architectures to remove unnecessary redundancy and to improve the inference speed. While many recent works focus on reducing the redundancy by eliminating unneeded weight parameters, it is not possible to apply a single deep network for multiple devices with different resources. When a new device or circumstantial condition requires a new deep architecture, it is necessary to construct and train a new network from scratch. In this work, we propose a novel deep learning framework, called a nested sparse network, which exploits an n-in-1-type nested structure in a neural network. A nested sparse network consists of multiple levels of networks with a different sparsity ratio associated with each level, and higher level networks share parameters with lower level networks to enable stable nested learning. The proposed framework realizes a resource-aware versatile architecture as the same network can meet diverse resource requirements, i.e., anytime property. Moreover, the proposed nested network can learn different forms of knowledge in its internal networks at different levels, enabling multiple tasks using a single network, such as coarse-to-fine hierarchical classification. In order to train the proposed nested network, we propose efficient weight connection learning and channel and layer scheduling strategies. We evaluate our network in multiple tasks, including adaptive deep compression, knowledge distillation, and learning class hierarchy, and demonstrate that nested sparse networks perform competitively, but more efficiently, compared to existing methods.

In this paper, we propose a generative model which learns the relationship between language and human action in order to generate a human action sequence given a sentence describing human behavior. The proposed generative model is a generative adversarial network (GAN), which is based on the sequence to sequence (SEQ2SEQ) model. Using the proposed generative network, we can synthesize various actions for a robot or a virtual agent using a text encoder recurrent neural network (RNN) and an action decoder RNN. The proposed generative network is trained from 29,770 pairs of actions and sentence annotations extracted from MSR-Video-to-Text (MSR-VTT), a large-scale video dataset. We demonstrate that the network can generate human-like actions which can be transferred to a Baxter robot, such that the robot performs an action based on a provided sentence. Results show that the proposed generative network correctly models the relationship between language and action and can generate a diverse set of actions from the same sentence.

This paper presents a control strategy synthesis method for dynamical systems with differential constraints while satisfying a set of given rules in consideration of their importances. A special attention is given to situations where all rules cannot be met in order to fulfill a given task. Such dilemmas compel us to make a decision on the degree of satisfaction of each rule including which rule should be maintained or not. In this work, we propose a learning-based model predictive control method in order to solve this problem, where a key insight is to combine a learning method and traditional control scheme so that the designed controller behaves close to human experts. A rule is represented as a signal temporal logic (STL) formula. A robustness slackness, a margin to the satisfaction of the rule, is learned from expert's demonstrations using Gaussian process regression. The learned margin is used in a model predictive control procedure, which helps to decide how much to obey each rule, even ignoring specific rules. In track driving simulation, we show that the proposed method generates human-like behavior and efficiently handles dilemmas as human teachers do.

In this paper, we propose an uncertainty-aware learning from demonstration method by presenting a novel uncertainty estimation method utilizing a mixture density network appropriate for modeling complex and noisy human behaviors. The proposed uncertainty acquisition can be done with a single forward path without Monte Carlo sampling and is suitable for real-time robotics applications. Then, we show that it can be decomposed into explained variance and unexplained variance where the connections between aleatoric and epistemic uncertainties are addressed. The properties of the proposed uncertainty measure are analyzed through three different synthetic examples, absence of data, heavy measurement noise, and composition of functions scenarios. We show that each case can be distinguished using the proposed uncertainty measure and presented an uncertainty-aware learning from demonstration method for autonomous driving using this property. The proposed uncertainty-aware learning from demonstration method outperforms other compared methods in terms of safety using a complex real-world driving dataset.

In this paper, we present a novel nonparametric motion flow model that effectively describes a motion trajectory of a human and its application to human robot cooperation. To this end, motion flow similarity measure which considers both spatial and temporal properties of a trajectory is proposed by utilizing the mean and variance functions of a Gaussian process. We also present a human robot cooperation method using the proposed motion flow model. Given a set of interacting trajectories of two workers, the underlying reward function of cooperating behaviors is optimized by using the learned motion description as an input to the reward function where a stochastic trajectory optimization method is used to control a robot. The presented human robot cooperation method is compared with the state-of-the-art algorithm, which utilizes a mixture of interaction primitives (MIP), in terms of the RMS error between generated and target trajectories. While the proposed method shows comparable performance with the MIP when the full observation of human demonstrations is given, it shows superior performance when partial trajectory information is given.

In this paper, we propose a novel maximum causal Tsallis entropy (MCTE) framework for imitation learning which can efficiently learn a sparse multi-modal policy distribution from demonstrations. We provide the full mathematical analysis of the proposed framework. First, the optimal solution of an MCTE problem is shown to be a sparsemax distribution, whose supporting set can be adjusted. The proposed method has advantages over a softmax distribution in that it can exclude unnecessary actions by assigning zero probability. Second, we prove that an MCTE problem is equivalent to robust Bayes estimation in the sense of the Brier score. Third, we propose a maximum causal Tsallis entropy imitation learning (MCTEIL) algorithm with a sparse mixture density network (sparse MDN) by modeling mixture weights using a sparsemax distribution. In particular, we show that the causal Tsallis entropy of an MDN encourages exploration and efficient mixture utilization while Boltzmann Gibbs entropy is less effective. We validate the proposed method in two simulation studies and MCTEIL outperforms existing imitation learning methods in terms of average returns and learning multi-modal policies.

In this paper, we propose a novel algorithm for learning from demonstration, which can learn a policy function robustly from a large number of demonstrations with mixed qualities. While most of the existing approaches assume that demonstrations are collected from skillful experts, the proposed method alleviates such restrictions by estimating the proficiency level of each demonstration using the proposed leverage optimization. Furthermore, a novel leveraged cost function is proposed to represent a policy function using deep neural networks by reformulating the objective function of leveraged Gaussian process regression using the representer theorem. The proposed method is successfully applied to autonomous track driving tasks, where a large number of demonstrations with mixed qualities are given as training data without labels.

A well-defined deformation model can be vital for non-rigid structure from motion (NRSfM). Most existing methods restrict the deformation space by assuming a fixed rank or smooth deformation, which are not exactly true in the real world, and they require the degree of deformation to be predetermined, which is impractical. Meanwhile, the errors in rotation estimation can have severe effects on the performance, i.e., these errors can make a rigid motion be misinterpreted as a deformation. In this paper, we propose an alternative to resolve these issues, motivated by an observation that non-rigid deformations, excluding rigid changes, can be concisely represented in a linear subspace without imposing any strong constraints, such as smoothness or low-rank. This observation is embedded in our new prior distribution, the Procrustean normal distribution (PND), which is a shape distribution exclusively for non-rigid deformations. Because of this unique characteristic of the PND, rigid and non-rigid changes can be strictly separated, which leads to better performance. The proposed algorithm, EM-PND, fits a PND to given 2D observations to solve NRSfM without any user-determined parameters. The experimental results show that EM-PND gives the state-of-the-art performance for the benchmark data sets, confirming the adequacy of the new deformation model.

This paper presents a cost-effective motion-planning method for robots operating in complex and realistic environments. While sampling-based path-planning algorithms, such as a rapidly exploring random tree (RRT) and its variants, have been highly effective for general path-planning problems, it is still difficult to find the minimum cost path in a complex space efficiently since RRT-based algorithms extend a search tree locally, requiring a large number of samples before finding a good solution. This paper presents an efficient nonmyopic path-planning algorithm by combining RRT*and a stochastic optimization method, called cross entropy. The proposed method constructs two RRT trees: The first tree is a standard RRT*tree, which is used to determine the nearest node in the tree to be extended to a randomly chosen point, and the second tree contains the first tree with additional long extensions. By maintaining two separate trees, we can grow the search tree nonmyopically to improve the efficiency of the algorithm while ensuring the asymptotic optimality of RRT*. From an extensive set of simulations and experiments using mobile and humanoid robots, we demonstrate that the proposed method consistently finds low-cost paths faster than the existing algorithms.

Recently, there have been many progresses for the problem of non-rigid structure reconstruction based on 2D trajectories, but it is still challenging to deal with complex deformations or restricted view ranges. Promising alternatives are the piecewise reconstruction approaches, which divide trajectories into several local parts and stitch their individual reconstructions to produce an entire 3D structure. These methods show the state-of-the-art performance, however, most of them are specialized for relatively smooth surfaces and some are quite complicated. Meanwhile, it has been reported numerously in the field of pattern recognition that obtaining consensus from many weak hypotheses can give a strong, powerful result. Inspired by these reports, in this paper, we push the concept of part-based reconstruction to the limit: Instead of considering the parts as explicitly-divided local patches, we draw a large number of small random trajectory sets. From their individual reconstructions, we pull out a statistic of each 3D point to retrieve a strong reconstruction, of which the procedure can be expressed as a sparse l1-norm minimization problem. In order to resolve the reflection ambiguity between weak (and possibly bad) reconstructions, we propose a novel optimization framework which only involves a single eigenvalue decomposition. The proposed method can be applied to any type of data and outperforms the existing methods for the benchmark sequences, even though it is composed of a few, simple steps. Furthermore, it is easily parallelizable, which is another advantage.

In this paper, we propose a novel method for robust learning from demonstration using leveraged Gaussian process regression. While existing learning from demonstration (LfD) algorithms assume that demonstrations are given from skillful experts, the proposed method alleviates such assumption by allowing demonstrations from casual or novice users. To learn from demonstrations of mixed quality, we present a sparse-constrained leveraged optimization algorithm using proximal linearized minimization. The proposed sparse constrained leverage optimization algorithm is successfully applied to sensory field reconstruction and direct policy learning for planar navigation problems. In experiments, the proposed sparse-constrained method outperforms existing LfD methods.

We propose a robust target tracking algorithm for a mobile robot under identity uncertainty, which arises in crowded environments. When a mobile robot has a sensor with a fan-shaped field of view and finite sensing region, the proposed algorithm aims to minimize the probability of losing a moving target. We predict the next position of a moving target in a crowded environment using a multiple-hypothesis prediction algorithm which combines the motion model and appearance model of the target. When the distribution of the target's next position follows a Gaussian mixture model, the proposed tracking algorithm can track a target with a guaranteed tracking success probability. If the tracking success probability is sufficiently good, the method minimizes the moving distance of the mobile robot. The performance of the method is extensively validated in simulation and experiments using a Pioneer robot with a Microsoft Kinect sensor.

In this paper, we propose Gaussian random paths by defining a probability distribution over continuous paths interpolating a finite set of anchoring points using Gaussian process regression. By utilizing the generative property of Gaussian random paths, a Gaussian random path planner is developed to safely steer a robot to a goal position. The Gaussian random path planner can be used in a number of applications, including local path planning for a mobile robot and trajectory optimization for whole body motion planning. We have conducted an extensive set of simulations and experiments, showing that the proposed planner outperforms look-ahead planners which use a pre-defined subset of egocentric trajectories in terms of collision rates and trajectory lengths. Furthermore, we apply the proposed method to existing trajectory optimization methods as an initialization step and demonstrate that it can help produce more cost-efficient trajectories.

To enable safe motion planning in a dynamic environment, it is vital to anticipate and predict object movements. In practice, however, an accurate object identification among multiple moving objects is extremely challenging, making it infeasible to accurately track and predict individual objects. Furthermore, even for a single object, its appearance can vary significantly due to external effects, such as occlusions, varying perspectives, or illumination changes. In this paper, we propose a novel recurrent network architecture called a recurrent flow network that can infer the velocity of each cell and the probability of future occupancy from a sequence of occupancy grids which we refer to as an occupancy flow. The parameters of the recurrent flow network are optimized using Bayesian optimization. The proposed method outperforms three baseline optical flow methods, Lucas-Kanade, Lucas-Kanade with Tikhonov regularization, and HornSchunck methods, and a Bayesian occupancy grid filter in terms of both prediction accuracy and robustness to noise.

In this paper, we propose a novel inverse reinforcement learning algorithm with leveraged Gaussian processes that can learn from both positive and negative demonstrations. While most existing inverse reinforcement learning (IRL) methods suffer from the lack of information near low reward regions, the proposed method alleviates this issue by incorporating (negative) demonstrations of what not to do. To mathematically formulate negative demonstrations, we introduce a novel generative model which can generate both positive and negative demonstrations using a parameter, called proficiency. Moreover, since we represent a reward function using a leveraged Gaussian process which can model a nonlinear function, the proposed method can effectively estimate the structure of a nonlinear reward function.

In this paper, we propose a coordinated localization algorithm for mobile sensor networks with camera sensors to operate under Global Positioning System (GPS) denied areas or indoor environments. Mobile robots are partitioned into two groups. One group moves within the field of views of remaining stationary robots. The moving robots are tracked by stationary robots and their trajectories are used as spatiotemporal features. From these spatiotemporal features, relative poses of robots are computed using multiview geometry and a group of robots is localized with respect to the reference coordinate based on the proposed multirobot localization. Once poses of all robots are recovered, a group of robots moves from one location to another while maintaining the formation of robots for coordinated localization under the proposed multirobot navigation strategy. By taking the advantage of a multiagent system, we can reliably localize robots over time as they perform a group task. In experiment, we demonstrate that the proposed method consistently achieves a localization error rate of 0.37% or less for trajectories of length between 715 cm and 890 cm using an inexpensive off-the-shelf robotic platform.

Recently, finding the low-dimensional structure of high-dimensional data has gained much attention. Given a set of data points sampled from a single subspace or a union of subspaces, the goal is to learn or capture the underlying subspace structure of the data set. In this paper, we propose elastic-net subspace representation, a new subspace representation framework using elastic-net regularization of singular values. Due to the strong convexity enforced by elastic-net, the proposed method is more stable and robust in the presence of heavy corruptions compared with existing lasso-type rank minimization approaches. For discovering a single low-dimensional subspace, we propose a computationally efficient low-rank factorization algorithm, called FactEN, using a property of the nuclear norm and the augmented Lagrangian method. Then, ClustEN is proposed to handle the general case, in which the data samples are drawn from a union of multiple subspaces, for joint subspace clustering and estimation. The proposed algorithms are applied to a number of subspace representation problems to evaluate the robustness and efficiency under various noisy conditions, and experimental results show the benefits of the proposed method compared with existing methods.

This paper proposes a novel multi-target tracking method which jointly solves a data association problem using images from multiple cameras. In this work, the spatiotemporal data association problem is formulated as a multidimensional assignment problem (MDA). To achieve a fast, efficient, and easily implementable approximation algorithm, we solve the MDA problem approximately by solving a sequence of bipartite matching problems using random splitting and merging operations. In this formulation, we design a new cost function, considering the accuracy in 3D reconstruction, motion smoothness, visibility from cameras, starting/ending at entrance and exit zone, and false positive. Our approach reconstructs 3D trajectories that represent people’s movement as 3D cylinders whose locations are estimated considering all adjacent frames. The experiments illustrate the proposed method shows the state-of-the-art performance in challenging multi-camera datasets and the computational efficiency with 8 times faster computation than the existing BIP approach.

Learning a low-dimensional structure plays an important role in computer vision. Recently, a new family of methods, such as l1 minimization and robust principal component analysis, has been proposed for low-rank matrix approximation problems and shown to be robust against outliers and missing data. But these methods often require heavy computational load and can fail to find a solution when highly corrupted data are presented. In this paper, an elastic-net regularization based low-rank matrix factorization method for subspace learning is proposed. The proposed method finds a robust solution efficiently by enforcing a strong convex constraint to improve the algorithm's stability while maintaining the low-rank property of the solution. It is shown that any stationary point of the proposed algorithm satisfies the Karush-Kuhn-Tucker optimality conditions. The proposed method is applied to a number of low-rank matrix approximation problems to demonstrate its efficiency in the presence of heavy corruptions and to show its effectiveness and robustness compared to the existing methods.

In this paper, we consider the problem of estimating the gaze direction of a person from a low-resolution image. Under this condition, reliably extracting facial features is very difficult. We propose a novel head pose estimation algorithm based on compressive sensing. Head image patches are mapped to a large feature space using the proposed extensive, yet efficient filter bank. The filter bank is designed to generate sparse responses of color and gradient information, which can be compressed using random projection, and classified by a random forest. Extensive experiments on challenging datasets show that the proposed algorithm performs favorably against the state-of-the-art methods on head pose estimation in low-resolution images degraded by noise, occlusion, and blurring.

In this paper, we propose a novel regression method that can incorporate both positive and negative training data into a single regression framework. In detail, a leveraged kernel function for non-stationary Gaussian process regression is proposed. With this new kernel function, we can vary the correlation betwen two inputs in both positive and negative directions by adjusting leverage parameters. By using this property, the resulting leveraged non-stationary Gaussian process regression can anchor the regressor to the positive data while avoiding the negative data. We first prove the positive semi-definiteness of the leveraged kernel function using Bochner's theorem. Then, we apply the leveraged non-stationary Gaussian process regression to a real-time motion control problem. In this case, the positive data refer to what to do and the negative data indicate what not to do. The results show that the controller using both positive and negative data outperforms the controller using positive data only in terms of the collision rate given training sets of the same size.

This paper considers the problem of approximating a kernel matrix in an autoregressive Gaussian process regression (AR-GP) in the presence of measurement noises or natural errors for modeling complex motions of pedestrians in a crowded environment. While a number of methods have been proposed to robustly predict future motions of humans, it still remains as a difficult problem in the presence of measurement noises. This paper addresses this issue by proposing a structured low-rank matrix approximation method using nuclear-norm regularized l1-norm minimization in AR-GP for robust motion prediction of dynamic obstacles. The proposed method approximates a kernel matrix by finding an orthogonal basis using low-rank symmetric positive semi-definite matrix approximation assuming that a kernel matrix can be well represented by a small number of dominating basis vectors. The proposed method is suitable for predicting the motion of a pedestrian, such that it can be used for safe autonomous robot navigation in a crowded environment. The proposed method is applied to well-known regression and motion prediction problems to demonstrate its robustness and excellent performance compared to existing approaches.

This paper presents a robust target tracking algorithm for a mobile sensor with a fan-shaped field of view and finite sensing range. The goal of the mobile robot is to track a moving target such that the probability of losing the target is minimized. We assume that the distribution of the next position of a moving target can be estimated using a motion prediction algorithm. If the next position of a moving target has the Gaussian distribution, the proposed algorithm can guarantee the tracking success probability. In addition, the proposed method minimizes the moving distance of the mobile robot based on a bound on the tracking success probability. While the problem considered in this paper is a non-convex optimization problem, we derive analytical solutions which can be easily solved in real-time. The performance of the proposed method is evaluated extensively in simulation and validated in pedestrian following experiments using a Pioneer mobile robot with a Microsoft Kinect sensor.

Low-rank matrix approximation plays an important role in the area of computer vision and image processing. Most of the conventional low-rank matrix approximation methods are based on the l2 -norm (Frobenius norm) with principal component analysis (PCA) being the most popular among them. However, this can give a poor approximation for data contaminated by outliers (including missing data), because the l2 -norm exaggerates the negative effect of outliers. Recently, to overcome this problem, various methods based on the l1 -norm, such as robust PCA methods, have been proposed for low-rank matrix approximation. Despite the robustness of the methods, they require heavy computational effort and substantial memory for high-dimensional data, which is impractical for real-world problems. In this paper, we propose two efficient low-rank factorization methods based on the l1 -norm that find proper projection and coefficient matrices using the alternating rectified gradient method. The proposed methods are applied to a number of low-rank matrix approximation problems to demonstrate their efficiency and robustness. The experimental results show that our proposals are efficient in both execution time and reconstruction performance unlike other state-of-the-art methods.

Recovering a non-rigid 3D structure from a series of 2D observations is still a difficult problem to solve accurately. Many constraints have been proposed to facilitate the recovery, and one of the most successful constraints is smoothness due to the fact that most real-world objects change continuously. However, many existing methods require to determine the degree of smoothness beforehand, which is not viable in practical situations. In this paper, we propose a new probabilistic model that incorporates the smoothness constraint without requiring any prior knowledge. Our approach regards the sequence of 3D shapes as a simple stationary Markov process with Procrustes alignment, whose parameters are learned during the fitting process. The Markov process is assumed to be stationary because deformation is finite and recurrent in general, and the 3D shapes are assumed to be Procrustes aligned in order to discriminate deformation from motion. The proposed method outperforms the state-of-the-art methods, even though the computation time is rather moderate compared to the other existing methods.

In this paper, we propose a novel Gaussian process motion controller that can navigate through a crowded dynamic environment. The proposed motion controller predicts future trajectories of pedestrians using an autoregressive Gaussian process motion model (AR-GPMM) from the partially-observable egocentric view of a robot and controls a robot using an autoregressive Gaussian process motion controller (AR-GPMC) based on predicted pedestrian trajectories. The performance of the proposed method is extensively evaluated in simulation and validated experimentally using a Pioneer 3DX mobile robot with a Microsoft Kinect sensor. In particular, the proposed method shows over 68% improvement on the collision rate compared to a reactive planner and vector field histogram (VFH).

This paper considers the problem of modeling complex motions of pedestrians in a crowded environment. A number of methods have been proposed to predict the motion of a pedestrian or an object. However, it is still difficult to make a good prediction due to challenges, such as the complexity of pedestrian motions and outliers in a training set. This paper addresses these issues by proposing a robust autoregressive motion model based on Gaussian process regression using l1-norm based low-rank kernel matrix approximation, called PCGP-l1. The proposed method approximates a kernel matrix assuming that the kernel matrix can be well represented using a small number of dominating principal components, eliminating erroneous data. The proposed motion model is robust against outliers present in a training set and can reliably predict the motion of a pedestrian, such that it can be used by a robot for safe navigation in a crowded environment. The proposed method is applied to a number of regression and motion prediction problems to demonstrate its robustness and efficiency. The experimental results show that the proposed method considerably improves the motion prediction rate compared to other Gaussian process regression methods.

In this paper we propose an efficient method for the recognition of long and complex action streams. First, we design a new motion feature flow descriptor by composing low-level local features. Then a new data embedding method is developed in order to represent the motion flow as an one-dimensional sequence, whilst preserving useful motion information for recognition. Finally attentional motion spots (AMSs) are defined to automatically detect meaningful motion changes from the embedded one-dimensional sequence. An unsupervised learning strategy based on expectation maximization and a weighted Gaussian mixture model is then applied to the AMSs for each action class, resulting in an action representation which we refer to as Action Chart. The Action Chart is then used efficiently for recognizing each action class. Through comparison with the state-of-the-art methods, experimental results show that the Action Chart gives promising recognition performance with low computational load and can be used for abstracting long video sequences.

Non-rigid structure from motion is a fundamental problem in computer vision, which is yet to be solved satisfactorily. The main difficulty of the problem lies in choosing the right constraints for the solution. In this paper, we propose new constraints that are more effective for non-rigid shape recovery. Unlike the other proposals which have mainly focused on restricting the deformation space using rank constraints, our proposal constrains the motion parameters so that the 3D shapes are most closely aligned to each other, which makes the rank constraints unnecessary. Based on these constraints, we define a new class of probability distribution called the Procrustean normal distribution and propose a new NRSfM algorithm, EM-PND. The experimental results show that the proposed method outperforms the existing methods, and it works well even if there is no temporal dependence between the observed samples.

There is a growing interest in smart homes and predicting behaviors of inhabitants is a key element for the success of smart home services. In this paper, we propose two algorithms, DBN-ANN and DBN-R, based on the deep learning framework for predicting various activities in a home. We also address drawbacks of contrastive divergence, a widely used learning method for restricted Boltzmann machines, and propose an efficient online learning algorithm based on bootstrapping. From experiments using home activity datasets, we show that our proposed prediction algorithms outperform existing methods, such as a nonlinear SVM and k-means, in terms of prediction accuracy of newly activated sensors. In particular, DBN-R shows an accuracy of 43.9% (51.8%) for predicting newly activated sensors based on MIT home dataset 1 (dataset 2), while previous work based on the n-gram algorithm has shown an accuracy of 39% (43%) on the same dataset.

Smart camera networks have recently emerged as a new class of sensor network infrastructure that is capable of supporting high-power in-network signal processing and enabling a wide range of applications. In this article, we provide an exposition of our efforts to build a low-bandwidth wireless camera network platform, called CITRIC, and its applications in smart camera networks. The platform integrates a camera, a microphone, a frequency-scalable (up to 624 MHz) CPU, 16 MB FLASH, and 64 MB RAM onto a single device. The device then connects with a standard sensor network mote to form a wireless camera mote. With reasonably low power consumption and extensive algorithmic libraries running on a decent operating system that is easy to program, CITRIC is ideal for research and applications in distributed image and video processing. Its capabilities of in-network image processing also reduce communication requirements, which has been high in other existing camera networks with centralized processing. Furthermore, the mote easily integrates with other low-bandwidth sensor networks via the IEEE 802.15.4 protocol. To justify the utility of CITRIC, we present several representative applications. In particular, concrete research results will be demonstrated in two areas, namely, distributed coverage hole identification and distributed object recognition.

In this paper, we propose a cost-aware path planning algorithm for mobile robots. As a robot moves from one location to another, the robot is penalized by the cost at its current location. The overall cost of the robot is determined by the trajectory of the robot over the cost map. The goal of the proposed cost-aware path planning algorithm is to find the trajectory with the minimal cost. The cost map of a field can represent environmental parameters, such as temperature, humidity, chemical concentration, wireless signal strength, and stealthiness. For example, if the cost map represents packet drop rates at different locations, the minimum cost path between two locations is the path with the best possible communication, which is desirable when a robot operates under the environment with weak wireless signals. The proposed cost-aware path planning algorithm extends the rapidly-exploring random tree (RRT) algorithm by applying the cross entropy (CE) method for extending motion segments. We show that the proposed algorithm finds a path which is close to the near-optimal cost path and gives an outstanding performance compared to RRT and CE-based path planning methods through extensive simulation.

With various sensors in a smart phone, it is now possible to obtain information about a user and her surroundings, such as the location of a smartphone and the activity of the smartphone user, and the obtained context information is being used to provide new services to the users. In this paper, we propose VibePhone, which uses a built-in vibrator and accelerometer, for recognizing the type of surfaces contacted by a smart phone, enabling the sense of touch in smartphones. For humans and animals, the sense of touch is fundamental for both recognizing and learning the properties of objects. The sense of touch is obtained from the texture of an object and humans recognize the type of an object by scrubbing the surface with fingers. Since a smartphone cannot physically scrub the contacting surface, we emulate the touch by generating vibrations using a smartphone and propose a method to recognize the type of contacting objects. The recognition of the object type by vibration alone is an extremely difficult task, even for a human. However, we demonstrate that it is possible to distinguish object types into broad categories where a phone is usually placed, e.g., sofas, plastic tables, wooden tables, hands, backpacks, and pants pockets. The proposed VibePhone system achieves an accuracy over 85% on average. We have prototyped VibePhone on an Android-based smart phone which changes its background display based on the contacting surface. We envision that the haptic perception in future smart phones will enable new experiences to the users.

We propose a novel communication method between smart devices using a built-in vibrator and accelerometer. The proposed approach is ideal for low-rate private communication and its communication medium is an object on which smart devices are placed, such as tables and desks. When more than two smart devices are placed on an object and one device wants to transmit a message to the other devices, the transmitting device generates a sequence of vibrations. The vibrations are propagated through the object on which devices are placed. The receiving devices analyze their accelerometer readings to decode incoming messages. Unlike radio-based wireless communication where eavesdropping of private communication is possible without the knowledge of the user, the proposed method can guarantee privacy as long as the object used for communication is secured. The proposed method is implemented on Android smart phones and comprehensive experiments are conducted to show its feasibility.

We propose a probabilistic framework for modeling and predicting traffic patterns using information obtained from wireless sensor networks. For concreteness, we apply the proposed framework to a smart building application in which traffic patterns of humans are modeled and predicted through human detection and matching of their images taken from cameras at different locations. Experiments with more than 100,000 images of over 40 subjects demonstrate promising results in traffic pattern prediction using the proposed algorithm. The algorithm can also be applied to other applications, including surveillance, traffic monitoring, abnormality detection, and location-based services. In addition, the long-term deployment of the network can be used for security, energy conservation, and utilization improvement of smart buildings.

This paper presents Virtual Lock, a novel smartphone application for personal surveillance using camera sensor networks. The proposed system consists of a smart phone and a set of easily deployable wireless camera sensor motes and enables an inexpensive solution to continuous monitoring of one's surroundings. Once camera sensor motes are deployed, a user can define multiple regions of interest for each camera's view using a smart phone application. Then the camera sensor network monitors for any changes in the defined regions of interest. If an event is detected, e.g., when a valuable good inside a region of interest is missing, the Virtual Lock system notifies the user via her smart phone. This paper describes the Virtual Lock system and demonstrates the potential of camera sensor networks.

This paper presents recent advances in multiagent sensing and operation in dynamic environments. Technology trends point towards a fusion of wireless sensor networks with robotic swarms of mobile robots. In this paper, we discuss the coordination and collaboration between networked robotic systems, featuring algorithms for cooperative operations such as unmanned aerial vehicles (UAVs) swarming. We have developed cooperative actions of groups of agents such as probabilistic pursuit-evasion game for search and rescue operations, protection of resources, and security applications. We have demonstrated a hierarchical system architecture which provides wide-range sensing capabilities to unmanned vehicles through spatially deployed wireless sensor networks, highlighting the potential collaboration between wireless sensor networks and unmanned vehicles. This paper also includes a short review of our current research efforts in heterogeneous sensor networks, which is being evolved into mobile sensor networks with swarm mobility. In a very essential way, this represents the fusion of mobility of ensembles with the network embedded systems, the robotic sensor web.

In this paper, we consider mobile sensor networks that use spatiotemporal Gaussian processes to predict a wide range of spatiotemporal physical phenomena. Nonparametric Gaussian process regression that is based on truncated observations is proposed for mobile sensor networks with limited memory and computational power. We first provide a theoretical foundation of Gaussian process regression with truncated observations. In particular, we demonstrate that prediction using all observations can be well approximated by prediction using truncated observations under certain conditions. Inspired by the analysis, we then propose a centralized navigation strategy for mobile sensor networks to move in order to reduce prediction error variances at points of interest. For the case in which each agent has a limited communication range, we propose a distributed navigation strategy. Particularly, we demonstrate that mobile sensing agents with the distributed navigation strategy produce an emergent, swarming-like, collective behavior for communication connectivity and are coordinated to improve the quality of the collective prediction capability.

In this paper, we propose a novel approach for video stabilization using Markov random field (MRF) modeling and maximum a posteriori (MAP) optimization. We build an MRF model describing a sequence of unstable images and find joint pixel matchings over all image sequences with MAP optimization via Gibbs sampling. The resulting displacements of matched pixels in consecutive frames indicate the camera motion between frames and can be used to remove the camera motion to stabilize image sequences. The proposed method shows robust performance even when a scene has moving foreground objects and brings more accurate stabilization results. The performance of our algorithm is evaluated on outdoor scenes.

Camera networks are being used in more applications as different types of sensor networks are used to instrument large spaces. Here we show a method for localizing the cameras in a camera network to recover the orientation and position up to scale of each camera, even when cameras are wide-baseline or have different photometric properties. Using moving objects in the scene, we use an intra-camera step and an inter-camera step in order to localize. The intra-camera step compares frames from a single camera to build the tracks of the objects in the image plane of the camera. The inter-camera step uses these object image tracks from each camera as features for correspondence between cameras. We demonstrate this idea on both simulated and real data.

This paper considers the problem of pursuit evasion games (PEGs), where the objective of a group of pursuers is to chase and capture a group of evaders in minimum time with the aid of a sensor network. The main challenge in developing a real-time control system using sensor networks is the inconsistency in sensor measurements due to packet loss, communication delay, and false detections. We address this challenge by developing a real-time hierarchical control system, namedLochNess, which decouples the estimation of evader states from the control of pursuers via multiple layers of data fusion. The multiple layers of data fusion convert noisy, inconsistent, and bursty sensor measurements into a consistent set of fused measurements. Three novel algorithms are developed forLochNess: multisensor fusion, hierarchical multitarget tracking, and multiagent coordination algorithms. The multisensor fusion algorithm converts correlated sensor measurements into position estimates, the hierarchical multitarget tracking algorithm based on Markov chain Monte Carlo data association (MCMCDA) tracks an unknown number of targets, and the multiagent coordination algorithm coordinates pursuers to chase and capture evaders using robust minimum-time control. The control systemLochNessis evaluated in simulation and successfully demonstrated using a large-scale outdoor sensor network deployment.

On August 30, 2005, we successfully demonstrated a large-scale, real-time, surveillance and control application on a wireless sensor network. The task was to track multiple human targets walking through a 5041 square meter sensor field and dispatch simulated pursuers to capture them. We employed a multi-target tracking algorithm that was a combination of a multi-sensor fusion algorithm for fusing binary detections and a Markov chain Monte Carlo data association (MCMCDA) algorithm that can initiate and terminates tracks autonomously and is robust to a high level of false alarms and missing measurements, a common problem in sensor networks. The tracks were used by a multi-agent coordination and control algorithm to capture the evaders. We were able to demonstrate successful pursuit of two crossing targets and successful tracking of three targets moving through a 144 node sensor field. To the authors' best knowledge, this experiment is the largest demonstration to date of a real-time tracking and control system on a wireless sensor network that does not use classification information

Multiple-target tracking is a canonical application of sensor networks as it exhibits different aspects of sensor networks such as event detection, sensor information fusion, multi-hop communication, sensor management and decision making. The task of tracking multiple objects in a sensor network is challenging due to constraints on a sensor node such as short communication and sensing ranges, a limited amount of memory and limited computational power. In addition, since a sensor network surveillance system needs to operate autonomously without human operators, it requires an autonomous tracking algorithm which can track an unknown number of targets. In this paper, we develop a scalable hierarchical multiple-target tracking algorithm that is autonomous and robust against transmission failures, communication delays and sensor localization error.

In this work we consider the problem of pursuit evasion games (PEGs) where a group of pursuers is required to detect, chase and capture a group of evaders with the aid of a sensor network in minimum time. Differently from standards PEGs where the environment and the location of evaders is unknown and a probabilistic map is built based on the pursuer’s onboard sensors, here we consider a scenario where a sensor network, previously deployed in the region of concern, can detect the presence of moving vehicles and can relay this information to the pursuers. Here we propose a general framework for the design of a hierarchical control architecture that exploits the advantages of a sensor network by combining both centralized and decentralized real-time control algorithms. We also propose a coordination scheme for the pursuers to minimize the time-to-capture of all evaders. In particular, we focus on PEGs with sensor networks orbiting in space for artificial space debris detection and removal.

This paper considers the problem of tracking objects with sparsely located binary sensors. Tracking with a sensor network is a challenging task due to the inaccuracy of sensors and difficulties in sensor network localization. Based on the simplest sensor model, in which each sensor reports only a binary value indicating whether an object is present near the sensor or not, we present an optimal distributed tracking algorithm which does not require sensor network localization. The tracking problem is formulated as a hidden state estimation problem over the finite state space of sensors. Then a distributed tracking algorithm is derived from the Viterbi algorithm. We also describe provably good pruning strategies for scalability of the algorithm and show the conditions under which the algorithm is robust against false detections. The algorithm is also extended to handle non-disjoint sensing regions and to track multiple moving objects. Since the computation and storage of track information are done in a completely distributed manner, the method is robust against node failures and transmission failures. In addition, the use of binary sensors makes the proposed algorithm suitable for many sensor network applications.