Russ Tedrake received his BSE in Computer Engineering from the University of Michigan (1999) and PhD in Electrical Engineering and Computer Science from MIT (2004). After graduation he spent a year with the MIT Brain and Cognitive Sciences Department as a Postdoctoral Associate. Now, Tedrake is a professor at MIT in the Department of Electrical Engineering and Computer Science and a member of the Computer Science and Artificial Intelligence Laboratory. His research focuses on underactuated motor control systems in animals and machines that are capable of executing tasks and interacting with uncertain environments. Some of Tedrake’s awards include: NSF CAREER Award, MIT Jerome Saltzer Award for undergraduate teaching, DARPA Young Faculty Award in Mathematics, and named the Microsoft Research New Faculty Fellow.
Recent Works
Localizing External Contact Using Proprioceptive Sensors
In order for robots to interact safely and intelligently with its’ environment they must be able to reliably estimate and localize external contacts. This research study introduces Contact Particle Filter (CPF) which is a general algorithm for detecting and localizing external contacts on rigid body robots without the assistance for external sensing. CPF strives to find the external contact points that best explain the observed external joint torque and provides sensible estimates even when the external torque measurement is corrupted with noise.
Tactile and Physical Perception
The DARPA Robotics Challenges highlights the fact that modern robots and their algorithms do not react well to unpredictable or poorly modeled contact. Thus, this research aims to improve the robots’ ability to sense and recognize its contact situation at each moment. The robot will be able to improve its’ perception of the world by using full advantage of the information and structure supplied by contact sensors and the physics of contact.
Soft-Contact Modeling
This research has developed implicit-surface models of a soft skin in order to capture the rich kinematics of the physical interaction without increasing the modeling dimensions. The objective is to make optimization-based parameter estimation and control design tractable for soft robots. This project is about the development and experimental demonstration of a soft contact model that can describe large deformations at contact surfaces of dynamic robotic systems.