Backend
Cooperative Mobile Manipulation using Learned Dynamical Systems
arXiv cs.RO0 views
arXiv:2611.21198v1 Announce Type: new Abstract: Cooperative mobile manipulation requires robots to coordinate their motions while ensuring whole-body collision avoidance and preserving task-relevant behaviors. We propose CALDS (Cooperative Adaptation of Learned Dynamical Systems), a framework that enables mobile manipulators to adapt learned single-agent behaviors for coordinated execution. Building on individual dynamical systems (DSs) learned from demonstrations, CALDS enables cooperative adaptation through two key components: Cooperative Policy Selection, which identifies compatible combinations of learned policies, and Temporal Adaptation, which ensures collision-free cooperation while preserving the spatial structure and convergence properties of the original behaviors. We evaluate CALDS across three diverse scenarios: assistive dressing, restaurant cleaning and serving, and drawer opening and object placement. Quantitative results demonstrate its effectiveness in improving task success and enabling safe, coordinated simultaneous execution while maintaining fidelity to demonstrated behaviors.
Source:https://arxiv.org/abs/2611.21198PreviousPolygraph: Large-Scale Multi-Session Trajectory Optimization using Pose GraphsNextBoBDeLaN: Bounded-Bandwidth Context Adaptation for Deep Lagrangian Robot Control
Related posts

Kafka Producer Flow: The Seven Stages Between send() and the Callback
0dev.to
Kapitan generator releases, 9 to 15 November 2026
0dev.to
Laravel Redis Cache Stampede, Locks and Memory Limits
0dev.to
Keeping WPF pack URIs alive through obfuscation
0dev.to
Our agent reviews its own mistakes every day. Here is the loop, and the tests it produced
0dev.to
AWS Cloud Architecture for UK SMEs: One Reference Design
0dev.to