RESample: A Robust Data Augmentation Framework via Exploratory Sampling for Robotic Manipulation
This addresses robustness issues in robotic manipulation for AI systems, but it is incremental as it builds on existing imitation learning and data augmentation methods.
The paper tackles the problem of vision-language-action models struggling with out-of-distribution states in robotic manipulation due to lack of failure data in imitation learning datasets, and proposes RESample, an automated data augmentation framework that improves model robustness and generalization, as demonstrated through experiments on the LIBERO benchmark and real-world tasks.
Vision-Language-Action models (VLAs) have demonstrated remarkable performance on complex robotic manipulation tasks through imitation learning. However, existing imitation learning datasets contain only successful trajectories and lack failure or recovery data, especially for out-of-distribution (OOD) states where the robot deviates from the main policy due to minor perturbations or errors, leading VLA models to struggle with states deviating from the training distribution. To this end, we propose an automated OOD data augmentation framework named RESample through exploratory sampling. Specifically, we first leverage offline reinforcement learning to obtain an action-value network that accurately identifies sub-optimal actions under the current manipulation policy. We further sample potential OOD states from trajectories via rollout, and design an exploratory sampling mechanism that adaptively incorporates these action proxies into the training dataset to ensure efficiency. Subsequently, our framework explicitly encourages the VLAs to recover from OOD states and enhances their robustness against distributional shifts. We conduct extensive experiments on the LIBERO benchmark as well as real-world robotic manipulation tasks, demonstrating that RESample consistently improves the stability and generalization ability of VLA models.