Event
Paper on shared control framework for mobile robots accepted by IEEE T-RO
1 reports · 1 sources
Jinyu Zhang and other authors propose a shared control framework for mobile robots, whose core is to predict operator intent at the planning level and to use intent-domain constraints for path replanning; the authors jointly model intent-domain prediction and replanning as a Markov decision process and solve it via deep reinforcement learning. The paper has been accepted by IEEE Transactions on Robotics. The authors also designed a Voronoi-based human trajectory generation algorithm, enabling the model to be trained entirely in simulation without human participation or demonstration data. The authors state that simulation and real-user experiments show that, compared with existing assisted teleoperation methods, this method reduces operator burden and improves safety without reducing task efficiency.
Report timeline
- A Planning-Level Intention Prediction Framework for Mobile Robot Shared Control
The paper proposes a shared control framework for mobile robots with planning-level intention prediction, using an intention domain to constrain path replanning and jointly modeling intention-domain prediction and replanning as a Markov decision process solved via deep reinforcement learning. The authors also design a Voronoi-based human trajectory generation algorithm that allows the model to be trained entirely in simulation without human participation or demonstration data; simulations and real-world user studies show the method reduces operator workload and improves safety without degrading task efficiency.
arXiv cs.RO ·