Crowd-Aware Robot Navigation for Pedestrians with Multiple Collision Avoidance Strategies via Map-based Deep Reinforcement Learning

by   Shunyi Yao1, et al.

It is challenging for a mobile robot to navigate through human crowds. Existing approaches usually assume that pedestrians follow a predefined collision avoidance strategy, like social force model (SFM) or optimal reciprocal collision avoidance (ORCA). However, their performances commonly need to be further improved for practical applications, where pedestrians follow multiple different collision avoidance strategies. In this paper, we propose a map-based deep reinforcement learning approach for crowd-aware robot navigation with various pedestrians. We use the sensor map to represent the environmental information around the robot, including its shape and observable appearances of obstacles. We also introduce the pedestrian map that specifies the movements of pedestrians around the robot. By applying both maps as inputs of the neural network, we show that a navigation policy can be trained to better interact with pedestrians following different collision avoidance strategies. We evaluate our approach under multiple scenarios both in the simulator and on an actual robot. The results show that our approach allows the robot to successfully interact with various pedestrians and outperforms compared methods in terms of the success rate.


page 1

page 4

page 6

page 7


Distributed Multi-Robot Obstacle Avoidance via Logarithmic Map-based Deep Reinforcement Learning

Developing a safe, stable, and efficient obstacle avoidance policy in cr...

Learning to Socially Navigate in Pedestrian-rich Environments with Interaction Capacity

Existing navigation policies for autonomous robots tend to focus on coll...

L2B: Learning to Balance the Safety-Efficiency Trade-off in Interactive Crowd-aware Robot Navigation

This work presents a deep reinforcement learning framework for interacti...

Safe Reinforcement Learning with Model Uncertainty Estimates

Many current autonomous systems are being designed with a strong relianc...

The effect of social groups on the dynamics of bi-directional pedestrian flow: a numerical study

We investigate the effect of groups on a bi-directional flow, by using n...

Collision Avoidance in Pedestrian-Rich Environments with Deep Reinforcement Learning

Collision avoidance algorithms are essential for safe and efficient robo...

Mapless Navigation among Dynamics with Social-safety-awareness: a reinforcement learning approach from 2D laser scans

We propose a method to tackle the problem of mapless collision-avoidance...

Please sign up or login with your details

Forgot password? Click here to reset