Event
RPT* and HATS: Target Search Planning with Probabilistic Endpoints
1 reports · 1 sources
Yunpeng Lyu and other authors propose the Hamiltonian Path Problem with Probabilistic Terminals (HPP-PT): a mobile robot must visit all candidate locations to find a target while minimizing expected path cost. The authors claim that their search method RPT* uses dynamic programming in a new state space to bypass history dependence, and is paired with heuristic acceleration for computation, with a guarantee of solution optimality. The HATS system based on RPT* combines Bayesian filtering or autonomous exploration. The authors report in simulation and real-machine experiments that the system can balance exploitation and exploration and finds targets faster on average than baseline methods; this is the paper authors' experimental conclusion.
Report timeline
- RPT*: Global Planning with Probabilistic Terminals for Target Search in Complex Environments
The paper studies the Hamiltonian Path Problem with Probabilistic Terminals (HPP-PT), whose goal is for a mobile robot to visit all candidate locations to find a target while minimizing expected path cost. The authors propose RPT*, a search method with optimality guarantees that uses dynamic programming in a new state space to bypass history dependency, along with a heuristic to speed up computation. The RPT*-based HATS system, combined with Bayesian filtering or autonomous exploration, found targets faster than baseline methods on average in both simulation and real-robot experiments.
arXiv cs.RO ·