Search

This article proposes a novel learning-based control policy with strong generalizability to new environments that enables a mobile robot to navigate autonomously through spaces filled with both static obstacles and dense crowds of pedestrians. The policy uses a unique combination of input data to generate the desired steering angle and forward velocity: a short history of lidar data, kinematic data about nearby pedestrians, and a subgoal point. The policy is trained in a reinforcement learning setting using a reward function that contains a novel term based on velocity obstacles to guide the robot to actively avoid pedestrians and move toward the goal. Through a series of 3-D simulated experiments with up to 55 pedestrians, this control policy is able to achieve a better balance between collision avoidance and speed (i.e., higher success rate and faster average speed) than state-of-the-art model-based and learning-based policies, and it also generalizes better to different crowd sizes and unseen environments. An extensive series of hardware experiments demonstrate the ability of this policy to directly work in different real-world environments with different crowd sizes with zero retraining. Furthermore, a series of simulated and hardware experiments show that the control policy also works in highly constrained static environments on a different robot platform without any additional training. Lastly, several important lessons that can be applied to other robot learning systems are summarized.

The Benchmark Autonomous Robot Navigation (BARN) Challenge took place at the 2022 IEEE International Conference on Robotics and Automation (ICRA), in Philadelphia, PA, USA. The aim of the challenge was to evaluate state-of-the-art autonomous ground navigation systems for moving robots through highly constrained environments in a safe and efficient manner. Specifically, the task was to navigate a standardized differential drive ground robot from a predefined start location to a goal location as quickly as possible without colliding with any obstacles, both in simulation and in the real world. Five teams from all over the world participated in the qualifying simulation competition, three of which were invited to compete with one another at a set of physical obstacle courses at the conference center in Philadelphia. The competition results suggest that autonomous ground navigation in highly constrained spaces, despite seeming simple for experienced roboticists, is actually far from being a solved problem. In this article, we discuss the challenge, the approaches used by the top three winning teams, and lessons learned to direct future research.