The HCRL participated in developing an end-to-end autonomous delivery system for the UT campus, capable of bringing food items without human intervention. Here is a pointer to an article in Medium:
Virtual presentation and paper on coordinating simultaneous manipulation and locomotion for humanoids and dexterous legged robots.
S. Jorgensen, M. Vedantam, R. Gupta, H. Cappel, and L. Sentis, Finding Locomanipulation Plans Quickly in the Locomotion Constrained Manifold, IEEE International Conference on Robotics and Automation, 2020
During his thesis, Steven has develop theory and implementation that ultimately allowed the humanoid robot Valkyrie to be deployed in a real world setup. Great accomplishment!
Our paper, lead by former student Ye Zhao, PI Luis Sentis, and collaborators, Yinan Li, Ufuk Topcu and Jun Liu, Reactive Task and Motion Planning for Robust Whole-Body Dynamic Locomotion in Constrained Environments, is conditionally accepted to The International Journal of Robotics Research. It describes a symbolic planning and subsymbolic control architecture for humanoid robots to autonomously navigate in complex dynamic environments.
Our paper, lead by students Donghyun Kim, Steven Jorgensen, Jaemin Lee, Junhyeok Ahn, Jianwen Luo, and PI Luis Sentis, Dynamic Locomotion For Passive-Ankle Biped Robots And Humanoids Using Whole-Body Locomotion Control, is now accepted to The International Journal of Robotics Research. Congratulations to the team! It allows line foot robots such as Mercury and Draco to dynamically walk and recover from push disturbances using Whole-Body Controllers.
PI, Dr. Sentis, gave this talk for a 400 people general audience of all ages focusing on engaging K-12 students in robotics.
Introducing our work on control of liquid cooled viscoelastic bipedal robots. Apptronik developed for UT Austin this excellent humanoid lower body robot, dubbed DRACO, and students at UT’s HCRL lab devised actuator control algorithms and integrated Time-to-Velocity Reversal Locomotion and Whole-Body Locomotion Control algorithms. The result is unsupported dynamic balancing of DRACO. A link to the paper preprint is here (click on the image):