In this video, PI Luis Sentis talks about efficient actuation approaches for human-centered robots:

 

Link to IROS 2021 workshop “From Gears To Direct Drive: Recent Trends and Opportunities in Actuation”

Congratulations to Ce Xu, our recent student co-advised with the UPC for devising new methods to learn and predict the motion of soft materials such as towels using mixture of Gaussian Processes. More details will be available soon.

The HCRL is proud to share our new NSF National Research Traineeship on Ethical AI Training for Roboticists. Congratulations to all the participants and to the Good Systems Bridging Barriers Program.

Link to article

Congratulations to Junhyeok Ahn, Nicolas Brissonneau, Bingham He from the HCRL, and Nick Paine, Orion Campbell, and Nick Nichols, from Apptronik for this great work on augmenting forces of operators using full lower-body exoskeletons.

Link to Article

Our collaborative NSF National Research Traineeship grant has been awarded! Dubbed, the NRT-AI: Convergent, Responsible, and Ethical AI Training Experience for Roboticists (CREATE Roboticists) will fund and train multiple generations of PhD students at the intersection between robotics, autonomous systems and ethics. It will create a new portfolio program in ethical robotics to ensure that technology and academic leaders coming from this program have gained expertise and education towards the good use of robotics from a social and labor perspective. We will join forces with faculty across various departments at UT to create a unique program with diverse perspectives.

We have accomplished strength amplification using Apptronik’s SAGIT exoskeleton reducing significantly the effort of operators carrying payloads and performing repetitive movements.

Draco 3 is up and swinging using our motion planning and control software PnC.

Dr. Sentis attended last week Tesla’s AI Day. What an incredible event and ambition both in ai and robotics! The full presentation is further below:

 

  

Here, Junhyeok describes our work on training nested mixture of expert mdoels for data-efficient model-based reinforcement learning. In particular, we focus on learning mixture of expert representations of hybrid dynamical systems that engage in intermittent contacts, such as legged robots. You can access the paper by using the URL below:

http://proceedings.mlr.press/v144/ahn21a/ahn21a.pdf

 

Congratulations to Junhyeok, Steven and Seung-Hyeon for getting this paper accepted in Frontiers in Robotics and AI, exploring fast optimal control and motion planning to maneuver in rough terrains using humanoid robots.

Link to Paper (in Press): Click Here