University of Cambridge > Talks.cam > Cyber-Human Lab Seminar Series > Navigating by Touch: Haptic Monte Carlo Localisation for a Legged Robot

Navigating by Touch: Haptic Monte Carlo Localisation for a Legged Robot

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Slawomir Tadeja.

As part of the Cyber-Human Lab seminar at IfM, we have the pleasure of hosting two guest speakers from the Poznan University of Technology (PUT), Poznan, Poland. The seminars will run one after another from 12:00 to 13:15 in Seminar Room 2 at IfM, West Cambridge. The Cyber-Human Lab seminars are open to everybody.

Dr Michal Nowicki, Assistant Professor with PUT , will deliver the second of the two talks.

Abstract:

In this talk, I will describe our latest developments in haptic localization for a legged robot. First, I will present our approach with terrain classification that enables the blind localization of the robot using the dense map of the environment. Second, I will discuss our improved method that uses compressed haptic signals without explicit terrain class specification. Finally, I will show our latest trained haptic localization that learns terrain representation to improve localization performance and can work with a sparse terrain map to yield the first viable blind haptic localization in a practical teach-and-repeat scenario. The presented research is part of the H2020 THING project.

Presenters Bio:

Dr Michal R. Nowicki graduated from Poznan University of Technology (PUT), receiving B.Sc. in Computer Science and B.Sc. and M.Sc. in Automatic Control and Robotics. He received (with honours) PhD in Robotics in 2018 and is currently a Research Assistant Professor at the Institute of Robotics and Machine Intelligence at PUT . His research interests include simultaneous localization and mapping (SLAM), robot perception, computer vision, optimization-based techniques in robotics, and multi-sensory calibration.

This talk is part of the Cyber-Human Lab Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity