Autonomy Talks - Jen Jen Chung: Safe Robot Navigation in Dense Human Crowds

Autonomy Talks - 26/04/2021

Speaker: Dr. Jen Jen Chung, Autonomous Systems Lab, ETH Zürich

Title: Safe robot navigation in dense human crowds

Abstract: Navigating through human crowds is a tough challenge for a robot. Crowds can cause severe sensor occlusions and often don’t leave much free space for the robot to move in, leading to what’s known as the ”freezing robot problem”. As part of the EU H2020 CrowdBot project, we are developing navigation and motion planning algorithms that allow the robot to work with the flow of the crowd to get to its destination. In this talk, I will discuss two levels of robot crowd navigation. The first looks at how low-level sensor information, such as range measurements, can be processed to learn collision-free navigation policies. The second looks at the higher-level problem of planning sequences of robot-pedestrian interactions that leverage the full set of behaviour modalities available to the robot, including speech, gestures and touch, to enable efficient navigation in dense crowds.

If you want to know more, visit our webpage: https://idsc.ethz.ch/research-frazzol...