RCSP: Risk-Sensitive Conjectural Scenario Planning for Safe Dynamic Robot Navigation

2026-05-25

AI Summary

This work addresses the predictive near-miss problem in mobile robot navigation, where current safe velocities can lead to future paths being blocked by dynamic obstacles. To mitigate this, the authors propose Risk-aware Conjectural Scenario Planning (RCSP), a method that constructs lightweight local motion beliefs to sample short-term obstacle trajectories. RCSP integrates risk-sensitive evaluation—explicitly penalizing high-risk tail scenarios—with local safety verification to enable proactive risk avoidance. Implemented as a complementary module within the Nav2 navigation stack, RCSP significantly improves collision-free navigation performance and path quality in MuJoCo bottleneck scenarios. Furthermore, in transfer experiments using DynaBARN and Jackal platforms, it effectively reduces dynamic near-miss failure rates, demonstrating superior robustness compared to standard DWA and TEB planners.

Abstract

Mobile robots can fail before they collide: a velocity that is safe now may commit the robot to a passage that moving obstacles will soon close. We study this predictive near-miss commitment problem and propose Risk-Sensitive Conjectural Scenario Planning (RCSP), a planning layer that evaluates candidate commands against plausible short-horizon obstacle futures. RCSP maintains a lightweight belief over local motion conjectures, samples future interactions, penalizes high-risk tails, and executes through a local safety check. In controlled MuJoCo bottleneck tasks, the RCSP planner reaches the goal without collisions and yields higher secondary safety and path-quality point estimates than a non-adaptive predictor, with additional latency. In ROS2/Gazebo, adding the local safety layer to a standard Nav2 stack reduces dynamic near-miss failures. On official DynaBARN/Jackal transfer, tuned DWA and TEB remain stronger on strict benchmark success, revealing the boundary of the approach. These simulation results position RCSP as a predictive-risk module that complements existing navigation stacks in dynamic bottleneck regimes.

Problem

• dynamic navigation
• near-miss commitment
• predictive risk
• mobile robots
• obstacle avoidance

Innovation

• Risk-Sensitive Planning
• Conjectural Scenario Planning
• Dynamic Obstacle Avoidance
• Predictive Safety
• Mobile Robot Navigation