Event
Functional specialization of dual-arm controllers improves success rate in simulation
1 reports · 1 sources
Jingwen Li and other authors submitted a preprint studying how responsibility is organized in dual-arm control within a simulated musculoskeletal system containing two communication-loop controllers. Using a 2×2 design, the study compared differentiated versus shared controller goals and fixed versus balanced hand-task assignment: differentiated goals combined with fixed assignment consistent with contralateral control routing produced the strongest functional specialization, with a dual-arm success rate of 81.33% and the highest control efficiency. This advantage widened as motor noise increased and narrowed under stronger energy penalties. Under differentiated-fixed training, swapping the roles of the two hands reduced the success rate by 80.46 percentage points, whereas under shared-balanced training it reduced it by only 1.51 percentage points. These results come from a simulated system.
Report timeline
- Learning Functional Specialization for Dual-Arm Robot Control
The study compares, in a simulated musculoskeletal system with dual communication-loop controllers, the effects of differentiated versus shared controller objectives and fixed versus balanced hand-task assignments on dual-arm control using a 2×2 design. Functional specialization was strongest when differentiated objectives were combined with a fixed assignment consistent with contralateral control routing, achieving a dual-arm success rate of 81.33% and the highest control efficiency. This advantage widened as motor noise increased and narrowed under stronger energy penalties. Under differentiated-fixed training, swapping the roles of the two hands reduced the success rate by 80.46 percentage points, whereas under shared-balanced training it fell by only 1.51 percentage points.
arXiv cs.RO ·