Scalar field features such as extrema, contours, and saddle points are essential for applications in environmental monitoring, search and rescue, and resource exploration. Traditional navigation methods often rely on predefined trajectories, leading to inefficient and resource-intensive mapping. This paper introduces a new adaptive navigation framework that leverages learning techniques to enhance exploration efficiency and effectiveness in scalar fields, even under noisy data and obstacles. The framework employs Partial Differential Equations to model scalar fields and a Gaussian Process Regressor to estimate the fields and their gradients, enabling real-time path adjustments and obstacle avoidance. We provide a theoretical foundation for the approach and address several limitations found in existing methods. The effectiveness of our framework is demonstrated through simulation benchmarks and field experiments with an Autonomous Surface Vehicle, showing improved efficiency and adaptability compared to traditional methods and offering a robust solution for real-time environmental monitoring.

By harnessing fiducial markers as visual landmarks in the environment, Unmanned Aerial Vehicles (UAVs) can rapidly build precise maps and navigate spaces safely and efficiently, unlocking their potential for fluent collaboration and coexistence with humans. Existing fiducial marker methods rely on handcrafted feature extraction, which sacrifices accuracy. On the other hand, deep learning pipelines for marker detection fail to meet real-time runtime constraints crucial for navigation applications. In this work, we propose YoloTag —a real-time fiducial marker-based localization system. YoloTag uses a lightweight YOLO v8 object detector to accurately detect fiducial markers in images while meeting the runtime constraints needed for navigation. The detected markers are then used by an efficient perspective-n-point algorithm to estimate UAV states. However, this localization system introduces noise, causing instability in trajectory tracking. To suppress noise, we design a higher-order Butterworth filter that effectively eliminates noise through frequency domain analysis. We evaluate our algorithm through real-robot experiments in an indoor environment, comparing the trajectory tracking performance of our method against other approaches in terms of several distance metrics.

Network fusion has been recently explored as an approach for improving pedestrian detection performance. However, most existing fusion methods suffer from runtime efficiency, modularity, scalability, and maintainability due to the complex structure of the entire fused models, their end-to-end training requirements, and sequential fusion process. Addressing these challenges, this paper proposes a novel fusion framework that combines asymmetric inferences from object detectors and semantic segmentation networks for jointly detecting multiple pedestrians. This is achieved by introducing a consensus-based scoring method that fuses pair-wise pixel-relevant information from the object detector and the semantic segmentation network to boost the final confidence scores. The parallel implementation of the object detection and semantic segmentation networks in the proposed framework entails a low runtime overhead. The efficiency and robustness of the proposed fusion framework are extensively evaluated by fusing different state-of-the-art pedestrian detectors and semantic segmentation networks on a public dataset. The generalization of fused models is also examined on new cross pedestrian data collected through an autonomous car. Results show that the proposed fusion method significantly improves detection performance while achieving competitive runtime efficiency.

This paper addresses the multi-robot planning problem to generate trajectories for maximum information gathering from an area of interest. To solve this problem, the proposed framework first leverages a Gaussian Mixture Model (GMM) as prior knowledge for modeling informative regions in the target area. Taking samples from the GMM, informative robot paths are then computed that optimize the travel costs subject to energy budgets. Decomposing these paths into waypoints, robot trajectories are planned while respecting kinematic constraints and subsequently replanned online to avoid collisions among themselves. The GMM model is incrementally updated by incorporating the gathered information. We demonstrate that our framework can achieve a significant amount of information gain with the optimal travel distance. We also provide a realistic simulation with a team of mobile robots in a port infrastructure monitoring setting.

This paper presents a novel method for pedestrian detection and tracking by fusing camera and LiDAR sensor data. To deal with the challenges associated with the autonomous driving scenarios, an integrated tracking and detection framework is proposed. The detection phase is performed by converting LiDAR streams to computationally tractable depth images, and then, a deep neural network is developed to identify pedestrian candidates both in RGB and depth images. To provide accurate information, the detection phase is further enhanced by fusing multi-modal sensor information using the Kalman filter. The tracking phase is a combination of the Kalman filter prediction and an optical flow algorithm to track multiple pedestrians in a scene. We evaluate our framework on a real public driving dataset. Experimental results demonstrate that the proposed method achieves significant performance improvement over a baseline method that solely uses image-based pedestrian detection.

The framework of partially observable Markov decision processes (POMDPs) offers a standard approach to model uncertainty in many robot tasks. Traditionally, POMDPs are formulated with optimality objectives. In this article, we study a different formulation of POMDPs withBoolean objectives. For robotic domains that require a correctness guarantee of accomplishing tasks, Boolean objectives are natural formulations. We investigate the problem of POMDPs with a common Boolean objective:safe reachability, requiring that the robot eventually reaches a goal state with a probability above a threshold while keeping the probability of visiting unsafe states below a different threshold. Our approach builds upon the previous work that represents POMDPs with Boolean objectives using symbolic constraints. We employ a satisfiability modulo theories (SMTs) solver to efficiently search for solutions, i.e., policies or conditional plans that specify the action to take contingent on every possible event. A full policy or conditional plan is generally expensive to compute. To improve computational efficiency, we introduce the notion ofpartial conditional plansthat cover sampled events to approximate a full conditional plan. Our approach constructs a partial conditional plan parameterized by areplanning probability. We prove that the failure rate of the constructed partial conditional plan is bounded by the replanning probability. Our approach allows users to specify an appropriate bound on the replanning probability to balance efficiency and correctness. Moreover, we update this bound properly to quickly detect whether the current partial conditional plan meets the bound and avoid unnecessary computation. In addition, to further improve the efficiency, we cache partial conditional plans for sampled belief states and reuse these cached plans if possible. We validate our approach in several robotic domains. The results show that our approach outperforms a previous policy synthesis approach for POMDPs with safe-reachability objectives in these domains.Note to Practitioners—This article was motivated by two observations. On the one hand, in robotics applications where uncertainty in sensing and actions is present, the solution to the classical partially observable Markov decision process (POMDP) formulation is expensive to compute in general. On the other hand, in certain practical scenarios, formulations other than the classical POMDP make a lot of sense and can provide flexibility in balancing efficiency and correctness. This article considers a modified POMDP formulation that includes a Boolean objective, namely safe reachability. This article uses the notion of a partial conditional plan. Rather than explicitly enumerating all possible observations to construct a full conditional plan, this work samples a subset of all observations to ensure bounded replanning probability. Our theoretical and empirical results show that the failure rate of the constructed partial conditional plan is bounded by the replanning probability. Moreover, these partial conditional plans can be cached to further improve the performance. Our results suggest that for domains where replanning is easy, increasing the replanning probability bound usually leads to better scalability, and for domains where replanning is difficult or impossible in some states, we can decrease the bound and allocate more computation time to achieve a higher success rate. Hence, in certain cases, the practitioner can take advantage of their knowledge of the problem domain to scale to larger problems. Preliminary physical experiments suggest that this approach is applicable to real-world robotic domains, but it requires a discrete representation of the workspace. How to deal with continuous workspace directly is an interesting future direction.

In this work, we address the problem of detecting body parts of pedestrians using deep neural networks. In particular, we consider the occluded pedestrian detection problem in autonomous driving settings. While state-of-the-art deep neural models perform reasonably well for detecting full-body pedestrians, their performances are not satisfactory for occluded pedestrians. Introducing a new training strategy along with a fusion mechanism, we enhance the performance of the SSD-Mobilenet and the Faster R-CNN by utilizing body parts information to handle occluded pedestrians. We evaluate our method by training these two deep neural networks using a public dataset as well as our dataset. The performance of the two developed models is compared both in terms of detection accuracy and runtime efficiency.

Toward a global picture of the radiation exposure of an area, particularly for fast emergency response, a UAV based exploration method is proposed. Without a priori knowledge of the radiation field, it is difficult to select the region of interest (ROI) which includes all radiation sources. For the case of a single radiation source, a greedy algorithm may localize the source by finding the maximum radiation value. However, when multiple sources generate a hotspot in a cumulative manner, the hotspot position does not coincide with one of the source positions. Therefore, we propose an efficient exploration method to quickly localize the radiation sources using the following procedures: (1) ROI selection using topographic maps with specific radiation level selection methods and (2) source localization estimating the number of sources and their positions with incremental variational Bayes inference of Gaussian mixtures. Under three different conditions according to the number of sources and their positions, we have shown that the proposed model can reduce the ROI and significantly improve the estimation accuracy than existing methods.

This paper presents a 3D online path planning algorithm for Unmanned Aerial Vehicles (UAVs) equipped with limited range sensors and computational resources in unknown cluttered environments. Even though quadrotor UAVs are considered to be a promising technology for surveillance purposes in indoor environments and for close observation in outdoor urban areas, it is very difficult to achieve autonomous aerial navigation toward a goal avoiding unpredicted collisions. Furthermore, greater attention and effort should be aimed at improving the computational efficiency and performance of path planning algorithms. The proposed heuristic algorithm offers on-the-fly path findings with a lesser computational complexity. We demonstrate the efficiency of our algorithm in a real world scenario implemented using the V-REP simulator.