What question did this study set out to answer?

To enhance multi-robot collaborative search efficiency while addressing sparse rewards and control oscillations.

April 10, 2026ActuatorsOpen Access

Hierarchical Active Perception and Stability Control for Multi-Robot Collaborative Search in Unknown Environments

View Full Paper

Ask AI

Bookmark

Authors

This framework improves search efficiency and control stability in multi-robot systems, indicating better collaborative outcomes.

To enhance multi-robot collaborative search efficiency while addressing sparse rewards and control oscillations.
Developed a hierarchical active perception framework using multi-agent deep deterministic policy gradient (HAP-MADDPG).
Implemented global utility planning and local information aggregation to improve target discovery.
Introduced a stability control mechanism utilizing hysteresis logic and reward decay.
Achieved a success rate of 96.25% in target capture.
Reduced average search time to 216.3 steps.
Demonstrated smooth path trajectories, indicating effective navigation.

Xu et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark