Skip to content

Event

WAM: Training a World Model with Quadruped Locomotion Data for Navigation Planning

1 reports · 1 sources

WAM proposes and reproduces a quadruped robot navigation method: locomotion data generated by the robot under convex model predictive control is used to train a forward-dynamics world model, replacing hand-crafted steering laws with receding-horizon sampling-based planning, and combining A* global path planning with dynamic obstacle extrapolation to achieve navigation and obstacle avoidance. The report states that all numerical values in this method come from local reproduction experiments, and no validation results from other robot platforms or external scenarios are involved.

Report timeline

  1. WAM: Training a world model with quadruped robot locomotion data for navigation planning

    WAM trains a forward-dynamics world model on quadruped robot locomotion data collected under convex model predictive control, replaces hand-crafted steering laws with receding-horizon sampling planning, and combines A* global paths with dynamic obstacle extrapolation to achieve navigation and obstacle avoidance. The material states that all numerical values come from local reproduction experiments.

    Guyuehome ·

Related topics

Planning and decision makingMotion controlRobot models and learningData and simulationResearch papers

Interest trend

Current
3
Peak
7Nov 4 01:00
Past 24 hours
-51%

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.