V
主页
京东 11.11 红包
Safe Learning in Robotics by Claire Tomlin
发布人
Safe Learning in Robotics by Claire Tomlin (UC Berkeley), Nov 25, 2020 Abstract: In many applications of robot learning, guarantees that specifications are satisfied throughout the learning process are paramount. For the safety specification, we present a controller synthesis technique based on the computation of reachable sets, using optimal control and game theory. We present new methods for computing the reachable set, based on a functional approximation which has the potential to broadly alleviate its computational complexity. In the second part of the talk, we will present a toolbox of methods combining reachability with data-driven techniques, to enable performance improvement while maintaining safety. We will illustrate these “safe learning” methods on robotic platforms at Berkeley, including demonstrations of motion planning around people, and navigating in a priori unknown environments. Bio: Claire Tomlin is a Professor of Electrical Engineering and Computer Sciences at the University of California at Berkeley, where she holds the Charles A. Desoer Chair in Engineering. Claire received the B.A.Sc. in EE from the University of Waterloo in 1992, M.Sc. in EE from Imperial College, London, in 1993, and the PhD in EECS from Berkeley in 1998. She held the positions of Assistant, Associate, and Full Professor at Stanford from 1998-2007, and in 2005 joined Berkeley. Claire works in hybrid systems and control, and integrates machine learning methods with control theoretic methods in the field of safe learning. She works in air traffic systems, unmanned air vehicle systems, and in systems biology.
打开封面
下载高清视频
观看高清视频
视频下载器
Data-driven MPC: From Linear to Nonlinear Systems with Guarantees by F. Allgöwer
Learning Dynamics from Bilinear Observations by Sarah Dean
Direct Adaptive Learning of the LQR by Florian Dörfler
The Role of Adaptation in Learning, Safety, and Optimality by Anuradha Annaswamy
Data driven Control of Unknown Nonlinear Systems Using Extremum Seeking Controls
期货交易改变了我的人生,圆梦提车!!缝缝补补5年是值得的!
Safe and Efficient Exploration in Reinforcement Learning by Andreas Krause
辛苦写的论文被学院老师看上了,通讯和一作都保不住了,该怎么办?
A Constrained Control Perspective on Safe Learning-Based Control by M. Zeilinger
What Makes Learning to Control Easy or Hard?by Nikolai Matni
Real-time Distributed Decision Making in Networked Systems by Na Li
Safe Learning in Robotics by Claire Tomlin
Learning for Safety-Critical Control in Dynamical Systems by Yisong Yue
Control Design Based on Deep Learning by Draguna Vrabie
Control Barrier Functions & Neural Networks for Handling Risk and Uncertainty...
无论是大手还是小手,都是用来扎你的手!
The Provable Effectiveness of Policy Gradient Methods in Reinforcement Learning.
Walking the Boundary of Learning and Interaction by Dorsa Sadigh
Simple Agent, Complex Environment: Efficient Reinforcement Learning with Agent..
Hybrid Systems: Analysis And Control by Claire Tomlin @ CDC 2014
Driving the Elephant through the Landscape of Deep Networks Stefano Soatto
Data Auctions with Externalities by Munther Dahleh
On the Structure of Learning: What’s in the Black Box? by Patricio Antonio Vela
冰人呼吸法研讨会
Regret-Optimal Control by Babak Hassibi
彻底摆脱人际关系中的唯唯诺诺,记住四个字:「无欲则刚」
Learning Models and Constraints with Limited Data by Necmiye Ozay
Multi-agent Dynamical Systems: Misaligned Objectives, Equilibria, Learning, &...
Data-Driven Engineering and Process Control Education with Portable Labs
The Non-Stochastic Control Problem by Elad Hazan
Fast and Flexible Multi-Agent Decision-Making by Naomi Leonard @ CDC 2023
俞敏洪:女性的堕落导致整个国家的堕落
Scalable Distributed Control and Learning of Networked Dynamical Systems by N Li
Physics-Guided Data-Driven Modeling for Control in Additive Manufacturing
Set-Based Methods for Hierarchical Model Predictive Control & Beyond by J Koeln
Formal Methods for Safety-Critical Control by Calin Belta
Optimizing Intended Cost Functions by Anca Dragan
Safe, Interaction-Aware Decision Making and Control for Robot Autonomy by Pavone
Preference and Participation Dynamics in Learning Systems by Sarah Dean
Learning and Control for Safety, Efficiency, and Resiliency of Embodied AI