FutureRay: Control-Aligned Future Range for Agile Quadruped Navigation

2026-09-26

AI Summary

This study addresses the vulnerability of quadruped robots to path blockage by moving obstacles during locomotion command execution. It proposes a local planning framework that operates without retraining the underlying gait policy. By integrating depth perception with historical data, the method jointly predicts future traversable gaps and collision risks, while incorporating model-based reactive braking constraints to optimize trajectory generation. In simulation, the approach achieves a 93.3% task completion rate with significantly lower collision rates than baseline methods. Real-world experiments further demonstrate that the system proactively avoids dynamic obstacles and resumes progress toward its goal, effectively enhancing the agile obstacle avoidance capabilities of quadruped robots in dynamic environments.

Abstract

Moving obstacles can block a previously clear route while a quadruped robot executes a motion command. We investigate whether predicting changing clearance improves navigation when motion selection accounts for the robot footprint and the time needed to react and brake. We present FutureRay, which predicts ranges across viewing directions and future times, together with encounter risk, from depth-derived range history and observable robot motion. Training emphasizes near-term clearance and penalizes errors that overstate available space. A local planner queries the same forecast for candidate headings and combines it with current observations to check clearance around the robot footprint. Model-based reaction--braking limits guide speed selection, and the resulting velocity commands are passed to a fixed locomotion policy. In paired evaluations on 60 static and dynamic simulation scenes, FutureRay achieves 93.3% completion, compared with 75.0% for current-range persistence and 80.0% for Cartesian Kalman rollout, with perception, planning, and locomotion held fixed. FutureRay also records fewer collisions than both baselines. Qualitative trials on a physical quadruped show avoidance initiated while an obstacle is approaching the route, followed by renewed goal progress. These results show that joint range and encounter-risk prediction can improve obstacle avoidance without retraining the locomotion policy.

Problem

• quadruped navigation
• moving obstacles
• obstacle avoidance
• dynamic environments
• clearance prediction

Innovation

• future range prediction
• encounter risk
• control-aligned planning
• quadruped navigation
• dynamic obstacle avoidance