Receding-Horizon Next-Best-View Planning for Highly Occluded Target Perception
Receding-Horizon Next-Best-View Planning for Highly Occluded Target Perception
This research addresses the challenge of robotic perception in highly occluded environments by proposing a receding-horizon next-best-view (RH-NBV) planner. The method evaluates sequences of future viewpoints to progressively reveal unobserved regions of a target. Evaluated on both simulation and physical robots, RH-NBV achieves significantly higher target information recovery under heavy occlusion compared to conventional NBV approaches, with performance improvements attributed to multi-step reasoning.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Environment
- SimulationOpen source S4
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
nts rather than isolated views. RH-NBV is evaluated on a UR5e manipulator with an eye-in-hand RGB-D camera in simulation as well as on physical robot against a gradient-based NBV planner, and random search, using a coffee mug and Stanford bunny under controlled occlusion and a tomato plant with natural self-occlusion. Under heavy occlusion, RH-NBV achieves substantially higher target information recovery, reaching 63
Open source S4
Source：arXiv Robotics — research abstracts · arxiv.org