Creadapt's resilient hexapod robot

[Airicist]

resibots.eu

youtube.com/aneoshun

Jean-Baptiste Mouret

[Airicist]

Transferability-based Behavioral Repertoire Learning in robotics

Published on Mar 21, 2013

Numerous algorithms have been proposed to allow legged robots to learn to walk. However, their vast majority are devised to learn to walk along a straight line, which not sufficient to accomplish any real-world mission.

Here we introduce TBR-Learning, a new learning algorithm that simultaneously discovers several hundreds of simple walking controllers, one for each possible direction. By taking advantage of solutions that are usually discarded, TBR-Learning is substantially faster than independently learning each controller. Our technique relies on two methods: (1) novelty search with local competition, which comes from the artificial life research field and (2) the transferability approach, which combines simulations and real tests to optimize a policy. We evaluate this new technique on a hexapod robot. Results show that with only a few dozens of short experiments performed on the physical robot, the algorithm learns a collection of controllers that allows the robot to reach each point of its reachable space. Overall, TBR-Learning opens a new kind of learning algorithm that simultaneously optimizes all the achievable behaviors of a robot.

[Airicist]

Fast Damage Recovery in Robotics with The T-Resilience algorithm

Published on Apr 29, 2013

Other failure scenarios are presented in: https://youtu.be/dncuBUnfkA4

Abstract:
Damage recovery is critical for autonomous robots that need to operate for a long time without assistance. Most current methods are complex and costly because they require anticipating each potential damage in order to have a contingency plan ready. As an alternative, we introduce the T-resilience algorithm, a new algorithm that allows robots to quickly and autonomously discover compensatory behaviors in unanticipated situations. This algorithm equips the robot with a self-model and discovers new behaviors by learning to avoid those that perform differently in the self-model and in reality. Our algorithm thus does not identify the damaged parts but it implicitly searches for efficient behaviors that do not use them. We evaluate the T-Resilience algorithm on a hexapod robot that needs to adapt to leg removal, broken legs and motor failures; we compare it to stochastic local search, policy gradient and the self-modeling algorithm proposed by Bongard et al. The behavior of the robot is assessed on-board thanks to a RGB-D sensor and a SLAM algorithm. Using only 25 tests on the robot and an overall running time of 20 minutes, T-Resilience consistently leads to substantially better results than the other approaches.

Publications
"Fast Damage Recovery in Robotics with the T-Resilience Algorithm"

by S. Koos, A. Cully and J.-B. Mouret
2013

[Airicist]

Creadapt's resilient hexapod robot

Published on Feb 20, 2014

[Airicist]

Article "Hexapod Robot Gets Even Better at Being Indestructible"

by Evan Ackerman
July 28, 2014

[Airicist]

Supplementary Video S1 for "Robots that can adapt like natural animals"

Uploaded on Jun 29, 2014

Title: Damage Recovery in Robots via Intelligent Trial and Error

Authors: Antoine Cully, Jeff Clune and Jean-Baptiste Mouret

The video shows the Intelligent Trial and Error Algorithm in action for two different damage conditions: a leg that has lost power and a broken leg. Initially, when the robot is undamaged, a hand-designed, classic tripod gait, performs well. Once damage occurs, however, this reference gait no longer works. The Intelligent Trial and Error Algorithm is initiated and quickly finds fast, compensatory behaviors for both damage conditions.

[Airicist]

Supplementary video S2 for "Robots that can adapt like natural animals"

Uploaded on Jun 29, 2014

Title: : A Behavior Repertoire Containing Many Different Types of Walking Gaits
Authors: Antoine Cully, Jeff Clune, Jean-Baptiste Mouret

In the behavioral repertoire creation step, the MAP-Elites algorithm produces a collection of different types of walking gaits. The video shows several examples of the different types of behaviors that are produced, from classic hexapod gaits to more unexpected forms of locomotion.

[Airicist]

Robot creadapt

Published on Jan 21, 2015

First steps of the Creadapt robot. This a wheel-leg hybrid robot.

[Airicist]

Robots that can adapt like animals (Nature cover article)

Published on May 27, 2015

The Intelligent Trial and Error Algorithm introduced in the paper 'Robots that can adapt like animals' (Nature, 2015): the video shows two different robots that can adapt to a wide variety of injuries in under two minutes.

A six-legged robot adapts to keep walking even if two of its legs are broken, and a robotic arm learns how to correctly place an object even with several broken motors.

Full citation: Cully A, Clune J, Tarapore DT, Mouret J-B. Robots that can adapt like animals. Nature, 2015. 521.7553, (cover article).

[Airicist]

Injured robots learn to limp

Published on May 27, 2015

Like most computers, robots are highly efficient… until something goes wrong. But could they learn to adapt to mechanical faults? Scientists have been deliberately sabotaging walking robots to see how fast they learn to cope.

Read more on the story:
"'Instinctive' robot recovers from injury fast"
Restorative algorithm has potential to make a variety of machines resilient.

by Davide Castelvecchi
May 27, 2015