RAPIDDS Framework Unifies Task and Motion Adaptation for Human-Robot Collaboration
The RAPIDDS framework addresses challenges in human-robot teaming by modeling both spatial and temporal behaviors across multiple cycles. Effective collaboration in human workspaces requires optimizing joint plans, yet existing methods often isolate task-level and motion-level adaptation. Task-level approaches focus on allocation and scheduling but neglect spatial interference in close-proximity scenarios. Motion-level methods prioritize collision avoidance while overlooking broader task context. This research introduces a unified solution that learns individualized human capabilities and preferences through repeated interactions. The framework considers domains like manufacturing where multi-cycle structures enable adaptation over time. By integrating spatial behavior modeling of motion paths with temporal behavior analysis of task completion times, RAPIDDS aims to improve practical robot deployment. The paper was announced on arXiv with identifier 2604.19670v1 as a cross-type publication.
Key facts
- The RAPIDDS framework unifies task-level and motion-level adaptation for human-robot teaming
- It models both spatial behavior (motion paths) and temporal behavior (task completion times)
- The approach addresses challenges in optimizing joint human-robot plans
- Prior research typically considered task-level and motion-level adaptation in isolation
- Task-level methods optimize allocation and scheduling but ignore spatial interference
- Motion-level methods focus on collision avoidance but ignore broader task context
- The framework learns individualized human capabilities and preferences over multiple cycles
- The paper was announced on arXiv with identifier 2604.19670v1
Entities
Institutions
- arXiv