Chrome Extension
WeChat Mini Program
Use on ChatGLM

Rapidly Adaptable Legged Robots Via Evolutionary Meta-Learning

IEEE/RJS International Conference on Intelligent RObots and Systems (IROS)(2020)CCF C

Google | Columbia Univ

Cited 93|Views259
Abstract
Learning adaptable policies is crucial for robots to operate autonomously in our complex and quickly changing world. In this work, we present a new meta-learning method that allows robots to quickly adapt to changes in dynamics. In contrast to gradient-based meta-learning algorithms that rely on second-order gradient estimation, we introduce a more noise-tolerant Batch Hill-Climbing adaptation operator and combine it with meta-learning based on evolutionary strategies. Our method significantly improves adaptation to changes in dynamics in high noise settings, which are common in robotics applications. We validate our approach on a quadruped robot that learns to walk while subject to changes in dynamics. We observe that our method significantly outperforms prior gradient-based approaches, enabling the robot to adapt its policy to changes based on less than 3 minutes of real data.
More
Translated text
Key words
evolutionary strategies,high noise settings,robotics applications,quadruped robot,gradient-based approaches,adaptable legged robots,evolutionary meta-learning,adaptable policies,meta-learning method,meta-learning algorithms,second-order gradient estimation,noise-tolerant Batch Hill-Climbing adaptation operator,time 3.0 min
PDF
Bibtex
AI Read Science
AI Summary
AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.
Example
Background
Key content
Introduction
Methods
Results
Related work
Fund
Key content
  • Pretraining has recently greatly promoted the development of natural language processing (NLP)
  • We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
  • We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
  • The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
  • Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance
Try using models to generate summary,it takes about 60s
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Related Papers

Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms.

2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2021

被引用30

Evolving Gaits for Damage Control in a Hexapod Robot.

Proceedings of the Genetic and Evolutionary Computation Conference 2021

被引用4

RMA: Rapid Motor Adaptation for Legged Robots

2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2022

被引用205

Behavior Self-Organization Supports Task Inference for Continual Robot Learning

2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2021

被引用17

Model-free End-to-end Learning of Agile Quadrupedal Locomotion over Challenging Terrain.

Tastulek Haserbek, Ziyang Wen, Xiaobin Xie, Peng Zhao, Wenfu An
International Conference on Real-time Computing and Robotics (RCAR) 2022

被引用2

Sim-to-Real Transfer for Quadrupedal Locomotion Via Terrain Transformer.

2023 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, ICRA 2023

被引用4

Evolutionary Machine Learning in Robotics

Handbook of Evolutionary Machine Learning Genetic and Evolutionary Computation 2023

被引用0

Meta-Learning with Evolutionary Strategy for Resilience Optimization of Image Recognition System

Viacheslav Moskalenko,Artem Korobov, Anton Kudravcev, Maxym Boiko
2023 IEEE 12th International Conference on Intelligent Data Acquisition and Advanced Computing Systems Technology and Applications (IDAACS) 2023

被引用0

Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn
Chat Paper

要点】:本文提出了一种基于进化策略和Batch Hill-Climbing适应算子的元学习新方法,使四足机器人能在高噪声环境下快速适应动力学变化。

方法】:作者通过结合进化策略和噪声容忍性更高的Batch Hill-Climbing适应算子,开发了一种新的元学习方法。

实验】:在四足机器人学习走路的实验中,使用该方法使机器人能在不到3分钟内根据实际数据调整其策略,验证了该方法在动力学变化适应方面的优越性。数据集名称未提及。