OSCAR: Obstacle Survival Curves for Adaptive Robot Navigation

2026-05-31

AI Summary

This work addresses the challenge faced by mobile robots navigating in known maps when encountering transient obstacles: the difficulty of adaptively deciding whether to wait or detour based on obstacle type. The authors propose OSCAR, a novel framework that introduces survival analysis with right-censoring into robotic navigation. OSCAR employs a class-conditional survival model to online learn the distribution of obstacle clearance times and integrates this with a time-dependent graph planner incorporating obstacle memory to dynamically compute waiting thresholds for each blocked edge. Requiring fewer than 20 observations per obstacle class, the method approaches optimal travel time in simulation (error <1%) and significantly improves navigation performance within 50 real-world trials, enabling continual, cross-task adaptation and adaptive decision-making.

Abstract

A mobile robot following a graph of known routes can make costly navigation errors when a temporary obstacle blocks a critical edge: waiting too long behind a parked cart wastes time, but immediately rerouting around a person who would move in a few seconds is also inefficient. Standard reactive obstacle avoidance addresses local motion around obstacles, while fixed wait-or-reroute rules ignore how long different obstacle types tend to persist. We propose OSCAR: an adaptive survival-modeling framework for graph-based navigation with temporary blockages. Assuming obstacle class labels are available at encounter time, the robot learns class-conditioned residual clearance-time distributions from online experience, including right-censored observations when it reroutes before observing clearance. These survival models are integrated into a time-dependent graph planner that maintains obstacle memory and computes a patience threshold at each blocked edge: how long to wait before taking an alternate route. The method continuously updates its clearance estimates across episodes and uses them to balance waiting against rerouting. We evaluate the approach in simulation and on a real mobile robot in a university atrium with obstacles including people, chairs, bins, and tubes. In simulation, the learned policy's time-to-goal converges to within 1% of an oracle with access to ground-truth clearance distributions after fewer than 20 observations per obstacle class, outperforming all heuristic baselines. Real-world deployment confirms that the policy improves online, adapting its patience thresholds from experience across 50 navigation episodes.

Problem

• adaptive navigation
• temporary obstacles
• obstacle persistence
• mobile robot
• graph-based navigation

Innovation

• survival analysis
• adaptive navigation
• clearance-time modeling
• graph-based planning
• right-censored data