CSC-MPPI: A Novel Constrained MPPI Framework with DBSCAN for Reliable Obstacle Avoidance

2025-06-19

AI Summary

Traditional Model Predictive Path Integral (MPPI) control struggles to strictly satisfy state and control constraints in dynamic obstacle environments, and its weighted-average action selection inherently yields suboptimal trajectories. Method: This paper proposes the Constraint-Satisfying Control MPPI (CSC-MPPI) framework, the first to integrate primal-dual gradient projection—ensuring all iterations remain within the feasible region—with DBSCAN-based density clustering—replacing weighted averaging to enable deterministic, optimal action selection. Contribution/Results: CSC-MPPI achieves, for the first time, robust trajectory optimization without any constraint violation under strict state and input constraints. Extensive simulations and real-vehicle experiments demonstrate a 23% improvement in obstacle avoidance success rate in complex dynamic scenarios, zero constraint violations, and an average planning latency of under 10 ms per iteration—fully satisfying real-time requirements for 100 Hz closed-loop control.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

This paper proposes Constrained Sampling Cluster Model Predictive Path Integral (CSC-MPPI), a novel constrained formulation of MPPI designed to enhance trajectory optimization while enforcing strict constraints on system states and control inputs. Traditional MPPI, which relies on a probabilistic sampling process, often struggles with constraint satisfaction and generates suboptimal trajectories due to the weighted averaging of sampled trajectories. To address these limitations, the proposed framework integrates a primal-dual gradient-based approach and Density-Based Spatial Clustering of Applications with Noise (DBSCAN) to steer sampled input trajectories into feasible regions while mitigating risks associated with weighted averaging. First, to ensure that sampled trajectories remain within the feasible region, the primal-dual gradient method is applied to iteratively shift sampled inputs while enforcing state and control constraints. Then, DBSCAN groups the sampled trajectories, enabling the selection of representative control inputs within each cluster. Finally, among the representative control inputs, the one with the lowest cost is chosen as the optimal action. As a result, CSC-MPPI guarantees constraint satisfaction, improves trajectory selection, and enhances robustness in complex environments. Simulation and real-world experiments demonstrate that CSC-MPPI outperforms traditional MPPI in obstacle avoidance, achieving improved reliability and efficiency. The experimental videos are available at https://cscmppi.github.io

Problem

• Enhances trajectory optimization with strict constraints
• Improves obstacle avoidance using DBSCAN clustering
• Ensures reliable constraint satisfaction in complex environments

Innovation

• Integrates primal-dual gradient for constraint enforcement
• Uses DBSCAN to cluster sampled trajectories
• Selects optimal action from lowest cost cluster