Vision-Language Models (VLMs) have recently shown promising advancements in sequential decision-making tasks through task-specific fine-tuning. However, common fine-tuning methods, such as Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) techniques like Proximal Policy Optimization (PPO), present notable limitations: SFT assumes Independent and Identically Distributed (IID) data, while PPO focuses on maximizing cumulative rewards. These limitations often restrict solution diversity and hinder generalization in multi-step reasoning tasks. To address these challenges, we introduce a novel framework, GFlowVLM, a framework that fine-tune VLMs using Generative Flow Networks (GFlowNets) to promote generation of diverse solutions for complex reasoning tasks. GFlowVLM models the environment as a non-Markovian decision process, allowing it to capture long-term dependencies essential for real-world applications. It takes observations and task descriptions as inputs to prompt chain-of-thought (CoT) reasoning which subsequently guides action selection. We use task based rewards to fine-tune VLM with GFlowNets. This approach enables VLMs to outperform prior fine-tuning methods, including SFT and RL. Empirical results demonstrate the effectiveness of GFlowVLM on complex tasks such as card games (NumberLine, BlackJack) and embodied planning tasks (ALFWorld), showing enhanced training efficiency, solution diversity, and stronger generalization capabilities across both in-distribution and out-of-distribution scenarios. Project page is available at https://mk322.github.io/gflowvlm/.

Amodal completion, which is the process of inferring the full appearance of objects despite partial occlusions, is crucial for understanding complex human-object interactions (HOI) in computer vision and robotics. Existing methods, such as those that use pre-trained diffusion models, often struggle to generate plausible completions in dynamic scenarios because they have a limited understanding of HOI. To solve this problem, we've developed a new approach that uses physical prior knowledge along with a specialized multi-regional inpainting technique designed for HOI. By incorporating physical constraints from human topology and contact information, we define two distinct regions: the primary region, where occluded object parts are most likely to be, and the secondary region, where occlusions are less probable. Our multi-regional inpainting method uses customized denoising strategies across these regions within a diffusion model. This improves the accuracy and realism of the generated completions in both their shape and visual detail. Our experimental results show that our approach significantly outperforms existing methods in HOI scenarios, moving machine perception closer to a more human-like understanding of dynamic environments. We also show that our pipeline is robust even without ground-truth contact annotations, which broadens its applicability to tasks like 3D reconstruction and novel view/pose synthesis.

We present a novel mission-planning strategy for heterogeneous multi-robot teams, taking into account the specific constraints and capabilities of each robot. Our approach employs hierarchical trees to systematically break down complex missions into manageable sub-tasks. We develop specialized APIs and tools, which are utilized by Large Language Models (LLMs) to efficiently construct these hierarchical trees. Once the hierarchical tree is generated, it is further decomposed to create optimized schedules for each robot, ensuring adherence to their individual constraints and capabilities. We demonstrate the effectiveness of our framework through detailed examples covering a wide range of missions, showcasing its flexibility and scalability.

The driver warning system that alerts the human driver about potential risks during driving is a key feature of an advanced driver assistance system. Existing driver warning technologies, mainly the forward collision warning and unsafe lane change warning, can reduce the risk of collision caused by human errors. However, the current design methods have several major limitations. Firstly, the warnings are mainly generated in a one-shot manner without modeling the ego driver’s reactions and surrounding objects, which reduces the flexibility and generality of the system over different scenarios. Additionally, the triggering conditions of warning are mostly rule-based threshold-checking given the current state, which lacks the prediction of the potential risk in a sufficiently long future horizon. In this work, we study the problem of optimally generating driver warnings by considering the interactions among the generated warning, the driver behavior, and the states of ego and surrounding vehicles on a long horizon. The warning generation problem is formulated as a partially observed Markov decision process (POMDP). An optimal warning generation framework is proposed as a solution to the proposed POMDP. The simulation experiments demonstrate the superiority of the proposed solution to the existing warning generation methods.

We study the problem of estimating the body movements of a camera wearer from egocentric videos. Current methods for ego-body pose estimation rely on temporally dense sensor data, such as IMU measurements from spatially sparse body parts like the head and hands. However, we propose that even temporally sparse observations, such as hand poses captured intermittently from egocentric videos during natural or periodic hand movements, can effectively constrain overall body motion. Naively applying diffusion models to generate full-body pose from head pose and sparse hand pose leads to suboptimal results. To overcome this, we develop a two-stage approach that decomposes the problem into temporal completion and spatial completion. First, our method employs masked autoencoders to impute hand trajectories by leveraging the spatiotemporal correlations between the head pose sequence and intermittent hand poses, providing uncertainty estimates. Subsequently, we employ conditional diffusion models to generate plausible full-body motions based on these temporally dense trajectories of the head and hands, guided by the uncertainty estimates from the imputation. The effectiveness of our methods was rigorously tested and validated through comprehensive experiments conducted on various HMD setup with AMASS and Ego-Exo4D datasets. Project page: https://sgchi.github.io/dsposer

The widespread adoption of commercial autonomous vehicles (AVs) and advanced driver assistance systems (ADAS) may largely depend on their acceptance by society, for which their perceived trustworthiness and interpretability to riders are crucial. In general, this task is challenging because modern autonomous systems software relies heavily on black-box artificial intelligence models. Towards this goal, this paper introduces a novel dataset, Rank2Tell1, a multi-modal ego-centric dataset for Ranking the importance level and Telling the reason for the importance. Using various close and open-ended visual question answering, the dataset provides dense annotations of various semantic, spatial, temporal, and relational attributes of various important objects in complex traffic scenarios. The dense annotations and unique attributes of the dataset make it a valuable resource for researchers working on visual scene understanding and related fields. Furthermore, we introduce a joint model for joint importance level ranking and natural language captions generation to benchmark our dataset and demonstrate performance with quantitative evaluations.

Motion forecasting in highly interactive scenarios is a challenging problem in autonomous driving. In such scenarios, we need to accurately predict the joint behavior of interacting agents to ensure the safe and efficient navigation of autonomous vehicles. Recently, goal-conditioned methods have gained increasing attention due to their advantage in performance and their ability to capture the multimodality in trajec-tory distribution. In this work, we study the joint trajectory prediction problem with the goal-conditioned framework. In particular, we introduce a conditional-variational-autoencoder-based (CVAE) model to explicitly encode different interaction modes into the latent space. However, we discover that the vanilla model suffers from posterior collapse and cannot induce an informative latent space as desired. To address these issues, we propose a novel approach to avoid KL vanishing and induce an interpretable interactive latent space with pseudo labels. The proposed pseudo labels allow us to incorporate domain knowledge on interaction in a flexible manner. We motivate the proposed method using an illustrative toy example. In addition, we validate our framework on the Waymo Open Motion Dataset with both quantitative and qualitative evaluations.

A lack of sufficient situational awareness is a primary cause of traffic crashes due to human error. Redirecting a driver’s attention to critical objects is essential, but alerting driver about all critical objects can lead to distraction. This paper develops and evaluates an adaptive support system that incorporates drivers’ fixations as a proxy for their situational awareness. We implement an experimental system that detects a driver’s gaze on important objects in the traffic scene and adapts a cueing strategy in an augmented reality-based driver awareness assistance interface. We collect and analyze data from 15 participants and show that our adaptive support system strategy is effective without increasing the drivers’ cognitive workload. Finally, we show that our system can increase ratio of drivers’ fixations on critical objects in their view without significantly increasing dwell time per object.

Evolving effective coordination strategies in tightly coupled multi-agent settings with sparse team fitness evaluations is challenging. It relies on multiple agents simultaneously stumbling upon the goal state to generate a learnable feedback signal. In such settings, estimating an agent's contribution to the overall team performance is extremely difficult, leading to a well-known structural credit assignment problem. This problem is further exacerbated when agents must complete sub-tasks with added spatial and temporal constraints, and different sub-tasks may require different local skills. We introduce MAEDyS, Multiagent Evolution via Dynamic Skill Selection, a hybrid bi-level optimization framework that augments evolutionary methods with policy gradient methods to generate effective coordination policies. MAEDyS learns to dynamically switch between multiple local skills towards optimizing the team fitness. It adopts fast policy gradients to learn several local skills using dense local rewards. It utilizes an evolutionary process to optimize the delayed team fitness by recruiting the most optimal skill at any given time. The ability to switch between various local skills during an episode eliminates the need for designing heuristic mixing functions. We evaluate MAEDyS in complex multiagent coordination environments with spatial and temporal constraints and show that it outperforms prior methods.

This paper presents a modular in-pipeline climbing robot with a novel compliant foldable OmniCrawler mechanism. The robot has a series of 3 compliant foldable OmniCrawler modules interconnected by links via passive joints. The circular cross-section of the module enables a holonomic motion to facilitate the alignment of the robot in the direction of bends. Additionally, the crawler mechanism provides a fair amount of traction, even on slippery pipe surfaces. These advantages of crawler modules have been further augmented by incorporating active compliance in the module, which helps to negotiate sharp bends in small diameter pipes. Introducing compliance in the crawler module with a single chain-lugs assembly is the the key novelty of this design. For the desirable pipe diameter and curvature of the bends, the spring stiffness value for each passive joint is determined by formulating a constrained optimization problem using the quasi-static model of the robot. Moreover, a minimum friction coefficient value between the module-pipe surface which can be vertically climbed by the robot without slipping is estimated. The numerical simulation results have further been validated by experiments on real robot prototype.