Skip to main content

Pint of Robotics: Human Motion Prediction for Safe and Efficient Operation in Human Environments, Andrey Rudenko, Robert Bosch GmbH - Corporate Research

Date
Date
Wednesday 21 April 2021, 1700-1800
Location
Zoom (see below for registration link)

Speaker: Andrey Rudenko, Robert Bosch GmbH - Corporate Research

Title: Human Motion Prediction for Safe and Efficient Operation in Human Environments

When: Wednesday 21st April, 1700-1800

Where: Zoom (free but registration required)

Abstract: With growing numbers of intelligent systems in human environments, the ability of such systems to perceive, understand and anticipate human behavior becomes increasingly important. Specifically, predicting future positions of dynamic agents and planning considering such predictions are important tasks for intelligent vehicles, service robots and advanced visual surveillance systems. What makes this task challenging is that human motion is influenced by a large variety of factors, including the person’s intention, the presence, attributes and actions of other surrounding agents, the geometry and semantics of the environment. In this talk, I broadly overview various aspects of the human motion prediction problem for robots in human environments. The talk begins summarizing the literature on motion prediction in a new taxonomy, discussing limitations of the state-of-the-art approaches and outlining the open challenges. The talk goes on to cover our research on predicting long-term motion of people in cluttered and crowded spaces, learning occupancy priors in urban environments, collecting meaningful motion data and benchmarking predicted trajectories.

Short Bio: Andrey Rudenko is a research scientist at Robert Bosch GmbH - Corporate Research. He earned his PhD at the University of Örebro (Sweden) in the field of human motion prediction. He has received the M.Sc. in Robotics from the University of Freiburg (Germany). His research tackles predicting long-term motion trajectories of people in social and industrial settings, contributing to the EU FP7 project Spencer and the EU H2020 project ILIAD. He has co-authored multiple papers at IJRR, RA-L, ICRA, IROS and RO-MAN, which tackled various aspects of anticipating human motion, human-aware path planning and human-robot interaction.