arXiv subjects

Gabriel Guo

Publications and source records attributed to Gabriel Guo.

3 recordsLinked to original sources

arXiv2025

Model Predictive Adversarial Imitation Learning for Planning from Observation

Human demonstration data is often ambiguous and incomplete, motivating imitation learning approaches that also exhibit reliable planning behavior. A common paradigm to perform planning-from-demonstration involves learning a reward function via Inverse Reinforcement Learning (IRL) then deploying this reward via Model Predictive Control (MPC). Towards unifying these methods, we derive a replacement of the policy in IRL with a planning-based agent. With connections to Adversarial Imitation Learning, this formulation enables end-to-end interactive learning of planners from observation-only demonstrations. In addition to benefits in interpretability, complexity, and safety, we study and observe significant improvements on sample efficiency, out-of-distribution generalization, and robustness. The study includes evaluations in both simulated control benchmarks and real-world navigation experiments using few-to-single observation-only demonstrations.

cs.RO↗

arXiv2025

Wheeled Lab: Modern Sim2Real for Low-cost, Open-source Wheeled Robotics

Reinforcement Learning (RL) has been pivotal in recent robotics milestones and is poised to play a prominent role in the future. However, these advances can rely on proprietary simulators, expensive hardware, and a daunting range of tools and skills. As a result, broader communities are disconnecting from the state-of-the-art; education curricula are poorly equipped to teach indispensable modern robotics skills involving hardware, deployment, and iterative development. To address this gap between the broader and scientific communities, we contribute Wheeled Lab, an ecosystem which integrates accessible, open-source wheeled robots with Isaac Lab, an open-source robot learning and simulation framework, that is widely adopted in the state-of-the-art. To kickstart research and education, this work demonstrates three state-of-the-art zero-shot policies for small-scale RC cars developed through Wheeled Lab: controlled drifting, elevation traversal, and visual navigation. The full stack, from hardware to software, is low-cost and open-source. Videos and additional materials can be found at: https://uwrobotlearning.github.io/WheeledLab/

cs.RO↗

arXiv2023

DeepCollide: Scalable Data-Driven High DoF Configuration Space Modeling using Implicit Neural Representations

Collision detection is essential to virtually all robotics applications. However, traditional geometric collision detection methods generally require pre-existing workspace geometry representations; thus, they are unable to infer the collision detection function from sampled data when geometric information is unavailable. Learning-based approaches can overcome this limitation. Following this line of research, we present DeepCollide, an implicit neural representation method for approximating the collision detection function from sampled collision data. As shown by our theoretical analysis and empirical evidence, DeepCollide presents clear benefits over the state-of-the-art, as it relates to time cost scalability with respect to training data and DoF, as well as the ability to accurately express complex workspace geometries. We publicly release our code.

cs.RO↗