Lecture

Acquiring Data for Learning: Modern Approaches and Challenges

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

In course

MICRO-462: Learning and adaptive control for robots

To cope with constant and unexpected changes in their environment, robots need to adapt their paths rapidly and appropriately without endangering humans. this course presents method to react within millisecunds. ...

Description

This lecture introduces data-driven learning for optimal controller acquisition, focusing on modern approaches and challenges. It covers programming by demonstration, data-driven learning, reinforcement learning, inverse reinforcement learning, and motion representations. The instructor discusses teleoperation, kinesthetic teaching, observational learning, and various teleoperation interfaces. The lecture explores the correspondence problem, data sensitivity, and task variability in learning from demonstration. It also delves into modeling hitting tasks using dynamical systems-based control, teaching compliant control, and considerations for learning human skills through demonstration.

Instructor

Aude Billard

Expertise RoboticsMachine LearningArtificial IntelligenceHuman-Robot InteractionMechatronicsDynamical Systems ControlComputational Neuroscience Aude Billard is full professor and head of the LASA laboratory at the School of Engineering at the Swiss Institute of Technology Lausanne (EPFL), and the Director of the Swiss Innovation Booster on Robotics. Dr. Billard acts as the President of the IEEE Robotics and Automation Society (RAS), after serving in several roles in the administrative and executive committe

Official source

Related concepts (32)

Optimal control

Optimal control theory is a branch of mathematical optimization that deals with finding a control for a dynamical system over a period of time such that an objective function is optimized. It has numerous applications in science, engineering and operations research. For example, the dynamical system might be a spacecraft with controls corresponding to rocket thrusters, and the objective might be to reach the moon with minimum fuel expenditure.

Learning

Learning is the process of acquiring new understanding, knowledge, behaviors, skills, values, attitudes, and preferences. The ability to learn is possessed by humans, animals, and some machines; there is also evidence for some kind of learning in certain plants. Some learning is immediate, induced by a single event (e.g. being burned by a hot stove), but much skill and knowledge accumulate from repeated experiences. The changes induced by learning often last a lifetime, and it is hard to distinguish learned material that seems to be "lost" from that which cannot be retrieved.

Observational learning

Observational learning is learning that occurs through observing the behavior of others. It is a form of social learning which takes various forms, based on various processes. In humans, this form of learning seems to not need reinforcement to occur, but instead, requires a social model such as a parent, sibling, friend, or teacher with surroundings. Particularly in childhood, a model is someone of authority or higher status in an environment.

Telerobotics

Telerobotics is the area of robotics concerned with the control of semi-autonomous robots from a distance, chiefly using television, wireless networks (like Wi-Fi, Bluetooth and the Deep Space Network) or tethered connections. It is a combination of two major subfields, which are teleoperation and telepresence. Teleoperation indicates operation of a machine at a distance. It is similar in meaning to the phrase "remote control" but is usually encountered in research, academic and technical environments.

Autonomous robot

An autonomous robot is a robot that acts without recourse to human control. The first autonomous robots environment were known as Elmer and Elsie, which were constructed in the late 1940s by W. Grey Walter. They were the first robots in history that were programmed to "think" the way biological brains do and meant to have free will. Elmer and Elsie were often labeled as tortoises because of how they were shaped and the manner in which they moved. They were capable of phototaxis which is the movement that occurs in response to light stimulus.

Related lectures (64)

Robot Learning and Control

Covers learning and adaptive control for robots, focusing on real-time reactivity and path planning using dynamical systems.

Acquiring Data for Learning

Explores training robots through reinforcement learning and learning from demonstration, highlighting challenges in human-robot interaction and data collection.

Force Control with Dynamical Systems

Covers compliant and force control for robots using Dynamical Systems.

Compliant Control for Robots: Impedance and Variable Stiffness

Explores compliant control for robots through impedance and variable stiffness, enabling safe and adaptive interactions with the environment.

Landscape and Generalisation in Deep Learning