Lab2Car: A Versatile Wrapper for Deploying Experimental Planners in Complex Real-world Environments

TL;DR

Lab2Car is a versatile wrapper that transforms arbitrary motion planner outputs into safe, feasible trajectories, enabling real-world testing of diverse autonomous driving algorithms in complex urban environments.

Contribution

We introduce Lab2Car, a novel optimization-based wrapper that facilitates deploying and evaluating various motion planners in real-world autonomous driving scenarios.

Findings

Successfully deployed ML and classical planners in Las Vegas urban settings.

Handled complex scenarios like cut-ins, overtaking, and yielding.

Accelerated testing and development of autonomous driving algorithms.

Abstract

Human-level autonomous driving is an ever-elusive goal, with planning and decision making -- the cognitive functions that determine driving behavior -- posing the greatest challenge. Despite a proliferation of promising approaches, progress is stifled by the difficulty of deploying experimental planners in naturalistic settings. In this work, we propose Lab2Car, an optimization-based wrapper that can take a trajectory sketch from an arbitrary motion planner and convert it to a safe, comfortable, dynamically feasible trajectory that the car can follow. This allows motion planners that do not provide such guarantees to be safely tested and optimized in real-world environments. We demonstrate the versatility of Lab2Car by using it to deploy a machine learning (ML) planner and a classical planner on self-driving cars in Las Vegas. The resulting systems handle challenging scenarios, such as cut-ins, overtaking, and yielding, in complex urban environments like casino pick-up/drop-off areas. Our work paves the way for quickly deploying and evaluating candidate motion planners in realistic settings, ensuring rapid iteration and accelerating progress towards human-level autonomy.