Event
Research on Interaction-Aware Sampling-Based Motion Planning for Autonomous Surface Vehicles
1 reports · 1 sources
Elia Trevisan and co-authors submitted a paper proposing a decentralized motion planner based on model predictive path integral control that simultaneously computes the trajectory of the own vessel and trajectory predictions of other vessels, and encodes traffic rules as discontinuous costs without requiring smooth approximations. The authors report that, in a map taken from a real section of the Amsterdam canals, all 780 randomized runs reached the goal without collisions or deadlocks, outperforming optimization-based planners in the same field and versions that do not consider interaction. The authors also conducted outdoor validation on two scaled boat prototypes, with planning and localization running onboard at 10 Hz, completing head-on and crossing encounters without rule violations. The paper has been submitted to IEEE and has not yet been published.
Report timeline
- Interaction-Aware Sampling-Based Motion Planning for Autonomous Surface Vessels in Urban Waterways
The authors propose a decentralized motion planner based on model predictive path integral control that jointly computes the ego vessel's trajectory and predictions of other vessels' trajectories, encoding traffic rules as discontinuous costs without requiring smooth approximations. In maps taken from real sections of Amsterdam's canals, 780 randomized runs all reached their goals without collisions or deadlocks, outperforming an optimization-based planner designed for the same domain as well as a version of the proposed planner that does not account for interaction. Two scaled vessel prototypes completed head-on and crossing encounters without rule violations, planning and localizing onboard at 10 Hz in an outdoor environment.
arXiv cs.RO ·
Related topics
Interest trend
- Current
- 3
- Peak
- 4Nov 4 01:00
- Past 24 hours
- –
The trend compares participants observed throughout the same period, so its range may be smaller than the current interest count. Move or tap to inspect each hour; use the arrow keys on a keyboard.