Trajectory Planning for Automated Driving using Target Funnels

2025-03-31

AI Summary

To address trajectory planning jitter, decision latency, and erratic steering caused by perception noise in autonomous driving, this paper proposes a predictive trajectory planning method based on a target funnel. The approach replaces the conventional single deterministic reference trajectory with a dynamically updated temporal reference set, explicitly modeling road curvature uncertainty and establishing a perception–planning closed-loop adaptive mechanism. Technically, it integrates probabilistic road modeling, receding-horizon optimization, and nonlinear model predictive control (MPC) subject to funnel constraints, enabling real-time online adaptation and robust tracking. Experimental validation on real-world vehicle data demonstrates high tracking accuracy, a 56% reduction in computational overhead, and significant suppression of anomalous steering commands. To the best of our knowledge, this work is the first to realize uncertainty-aware, funnel-driven trajectory planning.

Technology Category

Planning, Routing, and Scheduling: Replanning and Plan RepairHumans and AI: Human-Aware Planning and Behavior PredictionIntelligent Robots: Motion and Path Planning

Application Category

User Modeling, Personalization and Recommendation: User modeling for targeted and personalized online advertisingResponsible Web: Machine-in-the-loop, human agency and autonomySearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Self-driving vehicles rely on sensory input to monitor their surroundings and continuously adapt to the most likely future road course. Predictive trajectory planning is based on snapshots of the (uncertain) road course as a key input. Under noisy perception data, estimates of the road course can vary significantly, leading to indecisive and erratic steering behavior. To overcome this issue, this paper introduces a predictive trajectory planning algorithm with a novel objective function: instead of targeting a single reference trajectory based on the most likely road course, tracking a series of target reference sets, called a target funnel, is considered. The proposed planning algorithm integrates probabilistic information about the road course, and thus implicitly considers regular updates to road perception. Our solution is assessed in a case study using real driving data collected from a prototype vehicle. The results demonstrate that the algorithm maintains tracking accuracy and substantially reduces undesirable steering commands in the presence of noisy road perception, achieving a 56% reduction in input costs compared to a certainty equivalent formulation.

Problem

• Overcoming erratic steering from noisy perception data
• Planning trajectories using probabilistic road course information
• Reducing steering input costs with target funnel approach

Innovation

• Uses target funnels for trajectory planning
• Integrates probabilistic road course information
• Reduces steering input costs significantly