arXiv subjects

Catherine Weaver

Publications and source records attributed to Catherine Weaver.

8 recordsLinked to original sources

arXiv2026

Augmentron: Scalable Multi-View Visual Augmentation for Robot Learning

Robot policies trained on visually narrow demonstrations can become sensitive to environmental features that are unrelated to the task. Existing generative augmentation methods can introduce visual diversity, but processing every frame and camera view independently is computationally expensive and may produce inconsistent observations across cameras and timestamps. We introduce Augmentron, a geometry-aware pipeline that generates reusable scene representations and renders them through recorded camera poses. This produces temporally and multi-view consistent environ- ment and workspace variations while preserving the robot, task objects, actions, and annotations. Across three physical manipulation tasks, replacing half of the real world training dataset with Augmentron data improves model success across three tasks for both in out-of-distribution distractor objects, and out-of-distribution workspace variation evaluations. In a separate comparison against alternate augmentation techniques, Augmentron achieves the highest pooled success in all three conditions. The results show that introducing augmented data to a data training recipe can help policies generalize to dynamic real-world settings.

cs.LG↗

arXiv2026

FineART: Fine-Grained Annotated Robotic Trajectory Dataset and Vision-Language-Action Model for Bimanual Manipulation

Robots operating in real-world environments must often execute complex, multi-step bimanual tasks over long horizons rather than single, isolated actions. Current manipulation datasets provide limited support for this capability: although single-arm datasets reach hundreds of thousands of trajectories, they typically provide only one high-level instruction per episode, while existing bimanual datasets provide subtask annotations for only part of their recorded hours. We present FineART, a densely annotated bimanual manipulation dataset comprising 40,543 episodes (1,718 hours) and 533,913 subtasks across 151 tasks. We also introduce FineART-VLA, a vision-language-action policy that predicts its own next subtask to guide its actions. Mid-training on FineART's subtask annotations improves FineART-VLA's success at following spatial instructions from 32.0% to 100.0%. With step-by-step human subtask guidance, success on unseen long-horizon tasks increases from 16.0% to 76.0%. Furthermore, FineART-VLA matches baseline performance on a new robot with 10x less fine-tuning data and generalizes zero-shot to unseen tasks. We open-source the full dataset, model weights, and training code.

cs.RO↗

arXiv2025

Residual-MPPI: Online Policy Customization for Continuous Control

Policies developed through Reinforcement Learning (RL) and Imitation Learning (IL) have shown great potential in continuous control tasks, but real-world applications often require adapting trained policies to unforeseen requirements. While fine-tuning can address such needs, it typically requires additional data and access to the original training metrics and parameters. In contrast, an online planning algorithm, if capable of meeting the additional requirements, can eliminate the necessity for extensive training phases and customize the policy without knowledge of the original training scheme or task. In this work, we propose a generic online planning algorithm for customizing continuous-control policies at the execution time, which we call Residual-MPPI. It can customize a given prior policy on new performance metrics in few-shot and even zero-shot online settings, given access to the prior action distribution alone. Through our experiments, we demonstrate that the proposed Residual-MPPI algorithm can accomplish the few-shot/zero-shot online policy customization task effectively, including customizing the champion-level racing agent, Gran Turismo Sophy (GT Sophy) 1.0, in the challenging car racing scenario, Gran Turismo Sport (GTS) environment. Code for MuJoCo experiments is included in the supplementary and will be open-sourced upon acceptance. Demo videos and code are available on our website: https://sites.google.com/view/residual-mppi.

cs.RO↗

arXiv2024

Skill-Critic: Refining Learned Skills for Hierarchical Reinforcement Learning

Hierarchical reinforcement learning (RL) can accelerate long-horizon decision-making by temporally abstracting a policy into multiple levels. Promising results in sparse reward environments have been seen with skills, i.e. sequences of primitive actions. Typically, a skill latent space and policy are discovered from offline data. However, the resulting low-level policy can be unreliable due to low-coverage demonstrations or distribution shifts. As a solution, we propose the Skill-Critic algorithm to fine-tune the low-level policy in conjunction with high-level skill selection. Our Skill-Critic algorithm optimizes both the low-level and high-level policies; these policies are initialized and regularized by the latent space learned from offline demonstrations to guide the parallel policy optimization. We validate Skill-Critic in multiple sparse-reward RL environments, including a new sparse-reward autonomous racing task in Gran Turismo Sport. The experiments show that Skill-Critic's low-level policy fine-tuning and demonstration-guided regularization are essential for good performance. Code and videos are available at our website: https://sites.google.com/view/skill-critic.

cs.LG↗

arXiv2024

BeTAIL: Behavior Transformer Adversarial Imitation Learning from Human Racing Gameplay

Imitation learning learns a policy from demonstrations without requiring hand-designed reward functions. In many robotic tasks, such as autonomous racing, imitated policies must model complex environment dynamics and human decision-making. Sequence modeling is highly effective in capturing intricate patterns of motion sequences but struggles to adapt to new environments or distribution shifts that are common in real-world robotics tasks. In contrast, Adversarial Imitation Learning (AIL) can mitigate this effect, but struggles with sample inefficiency and handling complex motion patterns. Thus, we propose BeTAIL: Behavior Transformer Adversarial Imitation Learning, which combines a Behavior Transformer (BeT) policy from human demonstrations with online AIL. BeTAIL adds an AIL residual policy to the BeT policy to model the sequential decision-making process of human experts and correct for out-of-distribution states or shifts in environment dynamics. We test BeTAIL on three challenges with expert-level demonstrations of real human gameplay in Gran Turismo Sport. Our proposed residual BeTAIL reduces environment interactions and improves racing performance and stability, even when the BeT is pretrained on different tracks than downstream learning. Videos and code available at: https://sites.google.com/berkeley.edu/BeTAIL/home.

cs.LG↗

arXiv2023

Active Exploration in Iterative Gaussian Process Regression for Uncertainty Modeling in Autonomous Racing

Autonomous racing creates challenging control problems, but Model Predictive Control (MPC) has made promising steps toward solving both the minimum lap-time problem and head-to-head racing. Yet, accurate models of the system are necessary for model-based control, including models of vehicle dynamics and opponent behavior. Both dynamics model error and opponent behavior can be modeled with Gaussian Process (GP) regression. GP models can be updated iteratively from data collected using the controller, but the strength of the GP model depends on the diversity of the training data. We propose a novel active exploration mechanism for iterative GP regression that purposefully collects additional data at regions of higher uncertainty in the GP model. In the exploration, a MPC collects diverse data by balancing the racing objectives and the exploration criterion; then the GP is re-trained. The process is repeated iteratively; in later iterations, the exploration is deactivated, and only the racing objectives are optimized. Thus, the MPC can achieve better performance by leveraging the improved GP model. We validate our approach in the highly realistic racing simulation platform Gran Turismo Sport of Sony Interactive Entertainment Inc for a minimum lap time challenge, and in numerical simulation of head-to-head. Our active exploration mechanism yields a significant improvement in the GP prediction accuracy compared to previous approaches and, thus, an improved racing performance.

eess.SY↗

arXiv2023

Outracing Human Racers with Model-based Planning and Control for Time-trial Racing

Autonomous racing has become a popular sub-topic of autonomous driving in recent years. The goal of autonomous racing research is to develop software to control the vehicle at its limit of handling and achieve human-level racing performance. In this work, we investigate how to approach human expert-level racing performance with model-based planning and control methods using the high-fidelity racing simulator Gran Turismo Sport (GTS). GTS enables a unique opportunity for autonomous racing research, as many recordings of racing from highly skilled human players can served as expert emonstrations. By comparing the performance of the autonomous racing software with human experts, we better understand the performance gap of existing software and explore new methodologies in a principled manner. In particular, we focus on the commonly adopted model-based racing framework, consisting of an offline trajectory planner and an online Model Predictive Control-based (MPC) tracking controller. We thoroughly investigate the design challenges from three perspective, namely vehicle model, planning algorithm, and controller design, and propose novel solutions to improve the baseline approach toward human expert-level performance. We showed that the proposed control framework can achieve top 0.95% lap time among human-expert players in GTS. Furthermore, we conducted comprehensive ablation studies to validate the necessity of proposed modules, and pointed out potential future directions to reach human-best performance.

cs.RO↗

arXiv2023

Double-Iterative Gaussian Process Regression for Modeling Error Compensation in Autonomous Racing

Autonomous racing control is a challenging research problem as vehicles are pushed to their limits of handling to achieve an optimal lap time; therefore, vehicles exhibit highly nonlinear and complex dynamics. Difficult-to-model effects, such as drifting, aerodynamics, chassis weight transfer, and suspension can lead to infeasible and suboptimal trajectories. While offline planning allows optimizing a full reference trajectory for the minimum lap time objective, such modeling discrepancies are particularly detrimental when using offline planning, as planning model errors compound with controller modeling errors. Gaussian Process Regression (GPR) can compensate for modeling errors. However, previous works primarily focus on modeling error in real-time control without consideration for how the model used in offline planning can affect the overall performance. In this work, we propose a double-GPR error compensation algorithm to reduce model uncertainties; specifically, we compensate both the planner's model and controller's model with two respective GPR-based error compensation functions. Furthermore, we design an iterative framework to re-collect error-rich data using the racing control system. We test our method in the high-fidelity racing simulator Gran Turismo Sport (GTS); we find that our iterative, double-GPR compensation functions improve racing performance and iteration stability in comparison to a single compensation function applied merely for real-time control.

cs.RO↗