English
Related papers

Related papers: Learning to Control Self-Assembling Morphologies: …

200 papers

Reinforcement learning is typically concerned with learning control policies tailored to a particular agent. We investigate whether there exists a single global policy that can generalize to control a wide variety of agent morphologies --…

Machine Learning · Computer Science 2020-07-10 Wenlong Huang , Igor Mordatch , Deepak Pathak

Designing robots by hand can be costly and time consuming, especially if the robots have to be created with novel materials, or be robust to internal or external changes. In order to create robots automatically, without the need for human…

Neural and Evolutionary Computing · Computer Science 2021-04-08 Emma Hjellbrekke Stensby , Kai Olav Ellefsen , Kyrre Glette

Evolution sculpts both the body plans and nervous systems of agents together over time. In contrast, in AI and robotics, a robot's body plan is usually designed by hand, and control policies are then optimized for that fixed design. The…

Artificial Intelligence · Computer Science 2017-12-14 Nick Cheney , Josh Bongard , Vytas SunSpiral , Hod Lipson

Control policy learning for modular robot locomotion has previously been limited to proprioceptive feedback and flat terrain. This paper develops policies for modular systems with vision traversing more challenging environments. These…

Robotics · Computer Science 2023-05-02 Julian Whitman , Howie Choset

Modular robots can be reconfigured to create a variety of designs from a small set of components. But constructing a robot's hardware on its own is not enough -- each robot needs a controller. One could create controllers for some designs…

Robotics · Computer Science 2022-11-01 Julian Whitman , Howie Choset

Human motion is highly diverse and dynamic, posing challenges for imitation learning algorithms that aim to generalize motor skills for controlling simulated characters. Previous methods typically rely on a universal full-body controller…

Computer Vision and Pattern Recognition · Computer Science 2025-02-21 Yiming Huang , Zhiyang Dou , Lingjie Liu

Multi-agent reinforcement learning has shown promise on a variety of cooperative tasks as a consequence of recent developments in differentiable inter-agent communication. However, most architectures are limited to pools of homogeneous…

Multiagent Systems · Computer Science 2019-09-13 Bowen Jing , William Yin

Soft robotics is a rapidly growing area of robotics research that would benefit greatly from design automation, given the challenges of manually engineering complex, compliant, and generally non-intuitive robot body plans and behaviors. It…

Robotics · Computer Science 2023-06-19 Alican Mertan , Nick Cheney

Learning effective continuous control policies in high-dimensional systems, including musculoskeletal agents, remains a significant challenge. Over the course of biological evolution, organisms have developed robust mechanisms for…

Robotics · Computer Science 2023-07-17 Cameron Berg , Vittorio Caggiano , Vikash Kumar

Biological and artificial agents need to deal with constant changes in the real world. We study this problem in four classical continuous control environments, augmented with morphological perturbations. Learning to locomote when the length…

Robotics · Computer Science 2023-10-10 Alberto Silvio Chiappa , Alessandro Marin Vargas , Alexander Mathis

Self-Modeling is the process by which an agent, such as an animal or machine, learns to create a predictive model of its own dynamics. Once captured, this self-model can then allow the agent to plan and evaluate various potential behaviors…

Robotics · Computer Science 2022-09-07 Robert Kwiatkowski , Yuhang Hu , Boyuan Chen , Hod Lipson

Humans are able to perform a myriad of sophisticated tasks by drawing upon skills acquired through prior experience. For autonomous agents to have this capability, they must be able to extract reusable skills from past experience that can…

Machine Learning · Computer Science 2019-05-24 Xue Bin Peng , Michael Chang , Grace Zhang , Pieter Abbeel , Sergey Levine

We introduce a novel co-design method for autonomous moving agents' shape attributes and locomotion by combining deep reinforcement learning and evolution with user control. Our main inspiration comes from evolution, which has led to wide…

Artificial Intelligence · Computer Science 2022-05-24 Zhiquan Wang , Bedrich Benes , Ahmed H. Qureshi , Christos Mousas

A hallmark of biological intelligence and control is combinatorial generalization: animals are able to learn various things, then piece them together in new combinations to produce appropriate outputs for new tasks. Inspired by the ability…

Neurons and Cognition · Quantitative Biology 2022-10-07 Sunny Duan , Mikail Khona , Adrian Bertagnoli , Sarthak Chandra , Ila Fiete

An attached arm can significantly increase the applicability of legged robots to several mobile manipulation tasks that are not possible for the wheeled or tracked counterparts. The standard hierarchical control pipeline for such legged…

Robotics · Computer Science 2022-10-19 Zipeng Fu , Xuxin Cheng , Deepak Pathak

In an attempt to confer robots with complex manipulation capabilities, dual-arm anthropomorphic systems have become an important research topic in the robotics community. Most approaches in the literature rely upon a great understanding of…

Robotics · Computer Science 2019-05-28 Èric Pairet , Paola Ardón , Michael Mistry , Yvan Petillot

Humanoid robots, as general-purpose physical agents, must integrate both intelligent control and adaptive morphology to operate effectively in diverse real-world environments. While recent research has focused primarily on optimizing…

Robotics · Computer Science 2025-10-06 Guiliang Liu , Bo Yue , Yi Jin Kim , Kui Jia

We study a novel architecture and training procedure for locomotion tasks. A high-frequency, low-level "spinal" network with access to proprioceptive sensors learns sensorimotor primitives by training on simple tasks. This pre-trained…

Robotics · Computer Science 2016-10-18 Nicolas Heess , Greg Wayne , Yuval Tassa , Timothy Lillicrap , Martin Riedmiller , David Silver

How can agents learn internal models that veridically represent interactions with the real world is a largely open question. As machine learning is moving towards representations containing not just observational but also interventional…

Machine Learning · Computer Science 2024-07-03 Hamza Keurti , Hsiao-Ru Pan , Michel Besserve , Benjamin F. Grewe , Bernhard Schölkopf

Morphological development is part of the way any human or animal learns. The learning processes starts with the morphology at birth and progresses through changing morphologies until adulthood is reached. Biologically, this seems to…

Robotics · Computer Science 2020-03-17 M. Naya-Varela , A. Faina , R. J. Duro
‹ Prev 1 2 3 10 Next ›