Distinguished Speaker Series in Robotics

We cordially invite you to join the
DISTINGUISHED SPEAKER SERIES IN ROBOTICS
Thursday, April 29, 12:00 – 1:30pm

Virtual Meeting – Zoom Link | Meeting ID: 928 6786 9946 | Passcode: 103234

https://northeastern.zoom.us/j/92867869946?pwd=VTA5R1EwRmZKUjdSeHRpYXpVM09Kdz09

Manual Skills and Dexterity in Robots and Humans

Aude Billard

Professor of Robotics, Swiss Federal Institute of Technology (EPFL), Switzerland

Part 1: Robots have moved from imitating humans to exceeding humans’ capabilities – sometimes: The design of robots’ manipulation capabilities is driven by our admiration for humans’ exquisite dexterity and motor agility. Yet, robots are far from reproducing the complexity of human cognition, for some skills robots do better than humans. Thanks to their powerful motors and the speed of computation of their computer-driven circuits, robots can beat humans in precision and reactivity. This talk will give an overview of several approaches developed at LASA to endow robots with the ability to react extremely rapidly in the face of unexpected changes in the environment, combining control with dynamical systems and machine learning. We use human demonstrations to guide the design of the controller’s parameters to modulate the compliance and to determine the range of feasible paths. A review of these algorithms will be accompanied with illustrations of their implementation for controlling uni-manual and bi-manual manipulation. I will conclude by showing some examples of super-human capabilities for catching objects with a dexterity that exceeds that of human beings.

Part 2: Understanding bimanual skill – a case study in watchmaking: Human dexterity still eludes largely robotics. In an effort to better understand and model this dexterity, we took on an adventure and decided to follow a cohort of apprentices at watchmaking, a craft unique in its requirement for precise control of finger movements. Precise control of force is also of essence to prevent breakage of the tiny, and often highly valuable, pieces. In a two-year long training, apprentice acquire the ability to go beyond their natural perception of touch, so as to sense when the piece clicks and the screw in. Most impressive is the ability with which they acquire unusual but efficient hand postures. Our study unveils how the two hands work in coordination to distribute control variables and achieve better precision than when using a single hand.

Bio: Aude Billard is professor in robotics at the School of Engineering at the Swiss Federal Institute of Technology in Lausanne (EPFL). Trained in physics and robotics, she has been a pioneer in the application of machine learning for robotic control and human-robot interactions. Billard’s research focuses on manual control and dexterity, inspired by human skill. Her work on robotics and human-robot interactions has been recognized numerous times by the Institute of Electrical and Electronics Engineers (IEEE) and she currently holds a leadership position on the executive committee of the IEEE Robotics and Automation Society (RAS) as the vice president of publication activities.

Presented by the Institute for Experiential Robotics and Action Club