DiSCo: Diffusion Sequence Copilots for Shared Autonomy
🤖 AI Summary
This work addresses the challenge of effectively integrating human intent with AI policies to enhance shared autonomy in high-dimensional, complex, or noisy environments. It introduces, for the first time, diffusion models into action sequence planning for shared autonomy, proposing a conditional diffusion policy that leverages user input as both a conditioning seed and an action refinement signal. This approach guides the generation of control sequences that align with expert strategies while remaining faithful to user intent. A tunable hyperparameter mechanism enables flexible balancing among expert consistency, user alignment, and system responsiveness. Evaluated on simulated driving and robotic arm manipulation tasks, the method significantly improves task success rates and operational fluency, demonstrating its effectiveness in complex human-AI collaborative scenarios.
Application Category
📝 Abstract
Shared autonomy combines human user and AI copilot actions to control complex systems such as robotic arms. When a task is challenging, requires high dimensional control, or is subject to corruption, shared autonomy can significantly increase task performance by using a trained copilot to effectively correct user actions in a manner consistent with the user's goals. To significantly improve the performance of shared autonomy, we introduce Diffusion Sequence Copilots (DiSCo): a method of shared autonomy with diffusion policy that plans action sequences consistent with past user actions. DiSCo seeds and inpaints the diffusion process with user-provided actions with hyperparameters to balance conformity to expert actions, alignment with user intent, and perceived responsiveness. We demonstrate that DiSCo substantially improves task performance in simulated driving and robotic arm tasks. Project website: https://sites.google.com/view/disco-shared-autonomy/
Problem
Research questions and friction points this paper is trying to address.
shared autonomy
human-AI collaboration
diffusion policy
action correction
user intent alignment
Innovation
Methods, ideas, or system contributions that make the work stand out.
diffusion policy
shared autonomy
action inpainting
human-AI collaboration
sequence planning
🔎 Similar Papers
No similar papers found.
