Efficient automatic design of robots
- URL: http://arxiv.org/abs/2306.03263v2
- Date: Wed, 5 Jul 2023 18:00:48 GMT
- Title: Efficient automatic design of robots
- Authors: David Matthews, Andrew Spielberg, Daniela Rus, Sam Kriegman, Josh
Bongard
- Abstract summary: We show for the first time de-novo optimization of a robot's structure to exhibit a desired behavior, within seconds on a single consumer-grade computer.
Unlike other gradient-based robot design methods, this algorithm does not presuppose any particular anatomical form.
This advance promises near instantaneous design, manufacture, and deployment of unique and useful machines for medical, environmental, vehicular, and space-based tasks.
- Score: 43.968830087704035
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Robots are notoriously difficult to design because of complex
interdependencies between their physical structure, sensory and motor layouts,
and behavior. Despite this, almost every detail of every robot built to date
has been manually determined by a human designer after several months or years
of iterative ideation, prototyping, and testing. Inspired by evolutionary
design in nature, the automated design of robots using evolutionary algorithms
has been attempted for two decades, but it too remains inefficient: days of
supercomputing are required to design robots in simulation that, when
manufactured, exhibit desired behavior. Here we show for the first time de-novo
optimization of a robot's structure to exhibit a desired behavior, within
seconds on a single consumer-grade computer, and the manufactured robot's
retention of that behavior. Unlike other gradient-based robot design methods,
this algorithm does not presuppose any particular anatomical form; starting
instead from a randomly-generated apodous body plan, it consistently discovers
legged locomotion, the most efficient known form of terrestrial movement. If
combined with automated fabrication and scaled up to more challenging tasks,
this advance promises near instantaneous design, manufacture, and deployment of
unique and useful machines for medical, environmental, vehicular, and
space-based tasks.
Related papers
- Text2Robot: Evolutionary Robot Design from Text Descriptions [3.054307340752497]
We introduce Text2Robot, a framework that converts user text specifications and performance preferences into physical quadrupedal robots.
Text2Robot enables rapid prototyping and opens new opportunities for robot design with generative models.
arXiv Detail & Related papers (2024-06-28T14:51:01Z) - Evolution and learning in differentiable robots [0.0]
We use differentiable simulations to rapidly and simultaneously optimize individual neural control of behavior across a large population of candidate body plans.
Non-differentiable changes to the mechanical structure of each robot in the population were applied by a genetic algorithm in an outer loop of search.
One of the highly differentiable morphologies discovered in simulation was realized as a physical robot and shown to retain its optimized behavior.
arXiv Detail & Related papers (2024-05-23T15:45:43Z) - Towards a Robust Soft Baby Robot With Rich Interaction Ability for Advanced Machine Learning Algorithms [25.85850890842541]
We build a robust, partially soft robotic limb with a large action space and rich sensory data stream from multiple cameras.
As a proof of concept, we train two contemporary machine learning algorithms to perform a simple target-finding task.
arXiv Detail & Related papers (2024-04-11T19:15:45Z) - HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation [50.616995671367704]
We present a high-dimensional, simulated robot learning benchmark, HumanoidBench, featuring a humanoid robot equipped with dexterous hands.
Our findings reveal that state-of-the-art reinforcement learning algorithms struggle with most tasks, whereas a hierarchical learning approach achieves superior performance when supported by robust low-level policies.
arXiv Detail & Related papers (2024-03-15T17:45:44Z) - RoboScript: Code Generation for Free-Form Manipulation Tasks across Real
and Simulation [77.41969287400977]
This paper presents textbfRobotScript, a platform for a deployable robot manipulation pipeline powered by code generation.
We also present a benchmark for a code generation benchmark for robot manipulation tasks in free-form natural language.
We demonstrate the adaptability of our code generation framework across multiple robot embodiments, including the Franka and UR5 robot arms.
arXiv Detail & Related papers (2024-02-22T15:12:00Z) - Robot Learning with Sensorimotor Pre-training [98.7755895548928]
We present a self-supervised sensorimotor pre-training approach for robotics.
Our model, called RPT, is a Transformer that operates on sequences of sensorimotor tokens.
We find that sensorimotor pre-training consistently outperforms training from scratch, has favorable scaling properties, and enables transfer across different tasks, environments, and robots.
arXiv Detail & Related papers (2023-06-16T17:58:10Z) - Exploring the effects of robotic design on learning and neural control [0.0]
dissertation focuses on the development of robotic bodies, rather than neural controllers.
I have discovered that robots can be designed such that they overcome many of the current pitfalls encountered by neural controllers in multitask settings.
arXiv Detail & Related papers (2023-06-06T15:17:34Z) - HERD: Continuous Human-to-Robot Evolution for Learning from Human
Demonstration [57.045140028275036]
We show that manipulation skills can be transferred from a human to a robot through the use of micro-evolutionary reinforcement learning.
We propose an algorithm for multi-dimensional evolution path searching that allows joint optimization of both the robot evolution path and the policy.
arXiv Detail & Related papers (2022-12-08T15:56:13Z) - REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy
Transfer [57.045140028275036]
We consider the problem of transferring a policy across two different robots with significantly different parameters such as kinematics and morphology.
Existing approaches that train a new policy by matching the action or state transition distribution, including imitation learning methods, fail due to optimal action and/or state distribution being mismatched in different robots.
We propose a novel method named $REvolveR$ of using continuous evolutionary models for robotic policy transfer implemented in a physics simulator.
arXiv Detail & Related papers (2022-02-10T18:50:25Z) - Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots [29.02903745467536]
We propose Evolution Gym, the first large-scale benchmark for co-optimizing the design and control of soft robots.
Our benchmark environments span a wide range of tasks, including locomotion on various types of terrains and manipulation.
We develop several robot co-evolution algorithms by combining state-of-the-art design optimization methods and deep reinforcement learning techniques.
arXiv Detail & Related papers (2022-01-24T18:39:22Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.