Risk-aware Integrated Task and Motion Planning for Versatile Snake Robots under Localization Failures

2025-02-27

AI Summary

To address the insufficient navigation robustness of snake-like robots under localization failure, this paper proposes BLISS: a risk-aware end-to-end task-and-motion planning (TAMP) framework integrating proprioceptive motion control with intermittent LiDAR scanning. The key contribution is the first equivalent reformulation of a risk-constrained hybrid partially observable Markov decision process (CC-HPOMDP) into a computationally tractable convex mixed-integer linear program (MILP), overcoming the historical-dependency-induced intractability inherent in conventional POMDP solvers. BLISS unifies chance-constrained modeling, MILP-based convex approximation, adaptive scanning scheduling, and unified TAMP optimization. Experimental validation on the EELS robotic platform demonstrates that BLISS achieves over a 10× speedup in planning time compared to state-of-the-art POMDP methods and reduces overall navigation time by more than 50% relative to traditional two-stage planning approaches.

Technology Category

• Planning, Routing, and Scheduling: Planning with Markov Models (MDPs, POMDPs)
• Intelligent Robots: Motion and Path Planning
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Snake robots enable mobility through extreme terrains and confined environments in terrestrial and space applications. However, robust perception and localization for snake robots remain an open challenge due to the proximity of the sensor payload to the ground coupled with a limited field of view. To address this issue, we propose Blind-motion with Intermittently Scheduled Scans (BLISS) which combines proprioception-only mobility with intermittent scans to be resilient against both localization failures and collision risks. BLISS is formulated as an integrated Task and Motion Planning (TAMP) problem that leads to a Chance-Constrained Hybrid Partially Observable Markov Decision Process (CC-HPOMDP), known to be computationally intractable due to the curse of history. Our novelty lies in reformulating CC-HPOMDP as a tractable, convex Mixed Integer Linear Program. This allows us to solve BLISS-TAMP significantly faster and jointly derive optimal task-motion plans. Simulations and hardware experiments on the EELS snake robot show our method achieves over an order of magnitude computational improvement compared to state-of-the-art POMDP planners and $>$ 50% better navigation time optimality versus classical two-stage planners.

Problem

• Risk-aware task and motion planning
• Localization failures in snake robots
• Convex Mixed Integer Linear Program

Innovation

• BLISS combines proprioception with scans
• Reformulated CC-HPOMDP as convex MILP
• Achieves significant computational speed improvement