Occlusion-Aware Consistent Model Predictive Control for Robot Navigation in Occluded Obstacle-Dense Environments

2025-03-06

AI Summary

To address safety and motion consistency challenges in robot navigation under severe occlusion and dense obstacle conditions, this paper proposes an occlusion-aware Consistent Model Predictive Control (CMPC) framework. Our key contributions are: (1) a novel adjustable risk-zone mechanism grounded in occlusion uncertainty modeling, enabling online dynamic risk boundary generation; (2) a shared-consensus backbone with multi-branch trajectory architecture that jointly optimizes exploration-exploitation trade-offs and motion smoothness; and (3) distributed optimization via the Alternating Direction Method of Multipliers (ADMM) to coordinate branch-level trajectory planning. Extensive simulations and real-world experiments on an Ackermann-steering robot demonstrate that CMPC significantly improves task success rate (+37%), reduces velocity fluctuation (<0.15 m/s), and robustly avoids occluded obstacles—outperforming state-of-the-art baselines.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Mixed Discrete/Continuous Planning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Ensuring safety and motion consistency for robot navigation in occluded, obstacle-dense environments is a critical challenge. In this context, this study presents an occlusion-aware Consistent Model Predictive Control (CMPC) strategy. To account for the occluded obstacles, it incorporates adjustable risk regions that represent their potential future locations. Subsequently, dynamic risk boundary constraints are developed online to ensure safety. The CMPC then constructs multiple locally optimal trajectory branches (each tailored to different risk regions) to balance between exploitation and exploration. A shared consensus trunk is generated to ensure smooth transitions between branches without significant velocity fluctuations, further preserving motion consistency. To facilitate high computational efficiency and ensure coordination across local trajectories, we use the alternating direction method of multipliers (ADMM) to decompose the CMPC into manageable sub-problems for parallel solving. The proposed strategy is validated through simulation and real-world experiments on an Ackermann-steering robot platform. The results demonstrate the effectiveness of the proposed CMPC strategy through comparisons with baseline approaches in occluded, obstacle-dense environments.

Problem

• Ensures safe robot navigation in occluded, obstacle-dense environments.
• Develops dynamic risk boundary constraints for obstacle avoidance.
• Balances exploration and exploitation with multiple optimal trajectory branches.

Innovation

• Occlusion-aware Consistent Model Predictive Control (CMPC) strategy
• Adjustable risk regions for occluded obstacles
• ADMM for parallel solving of CMPC sub-problems