Safe and Real-Time Consistent Planning for Autonomous Vehicles in Partially Observed Environments via Parallel Consensus Optimization

2024-09-16

arXiv.org

AI Summary

Addressing the challenge of jointly ensuring safety and trajectory consistency under partial observability in autonomous driving, this paper proposes the Consistent Parallel Trajectory Optimization (CPTO) framework. Methodologically, CPTO introduces (1) a novel Consensus Safety Barrier module, leveraging discrete-time barrier functions to guarantee motion safety across multiple environmental hypotheses; and (2) an ADMM-based parallel bi-convex trajectory optimization mechanism that decomposes the problem into low-dimensional quadratic programs to enable consensus trajectory segment sharing across scenarios. Evaluated on both synthetic and real-world traffic datasets, CPTO reduces safety violation rates by 37% and improves trajectory consistency by 52% over state-of-the-art methods, while maintaining single-cycle planning latency below 50 ms—satisfying real-time operational requirements.

Technology Category

• Search and Optimization: Learning to Search
• Constraint Satisfaction and Optimization: Constraint Optimization
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Ensuring safety and driving consistency is a significant challenge for autonomous vehicles operating in partially observed environments. This work introduces a consistent parallel trajectory optimization (CPTO) approach to enable safe and consistent driving in dense obstacle environments with perception uncertainties. Utilizing discrete-time barrier function theory, we develop a consensus safety barrier module that ensures reliable safety coverage within the spatiotemporal trajectory space across potential obstacle configurations. Following this, a bi-convex parallel trajectory optimization problem is derived that facilitates decomposition into a series of low-dimensional quadratic programming problems to accelerate computation. By leveraging the consensus alternating direction method of multipliers (ADMM) for parallel optimization, each generated candidate trajectory corresponds to a possible environment configuration while sharing a common consensus trajectory segment. This ensures driving safety and consistency when executing the consensus trajectory segment for the ego vehicle in real time. We validate our CPTO framework through extensive comparisons with state-of-the-art baselines across multiple driving tasks in partially observable environments. Our results demonstrate improved safety and consistency using both synthetic and real-world traffic datasets.

Problem

• Ensuring safety in partially observed autonomous driving environments
• Achieving real-time consistent trajectory planning with uncertainties
• Optimizing parallel computation for safe and consistent driving

Innovation

• Parallel consensus optimization for safe trajectories
• Discrete-time barrier function ensures safety
• ADMM accelerates computation via decomposition