Videos¶

The ResiBots project - interview with JB Mouret¶

Learning and adapting quadruped gaits with the “Intelligent Trial & Error” algorithm (ICRA, 2019)¶

Dalin, P. Desreumaux, J.-B. Mouret. (2019) Learning and adapting quadruped gaits with the “Intelligent Trial & Error” algorithm. ICRA Workshop on “Learning Legged Locomotion”. [pdf]

Using Parameterized Black-Box Priors to Scale Up Model-Based Policy Search for Robotics (ICRA, 2018)¶

K. Chatzilygeroudis, J.-B Mouret (2018). Using Parameterized Black-Box Priors to Scale Up Model-Based Policy Search for Robotics. IEEE International Conference on Robotics and Automation (ICRA) [pdf] [url] [video]

Bayesian Optimization with Automatic Prior Selection for Data-Efficient Direct Policy Search (ICRA, 2018)¶

R. Pautrat, K. Chatzilygeroudis, J.-B Mouret (2018). Bayesian Optimization with Automatic Prior Selection for Data-Efficient Direct Policy Search. IEEE International Conference on Robotics and Automation (ICRA) [pdf] [url] [video]

Adaptive and Resilient Soft Tensegrity Robots (Soft Robotics, 2018)¶

J. Rieffel*, J.-B Mouret* (2018). Adaptive and Resilient Soft Tensegrity Robots Soft Robotics. (* J. Rieffel and J.-B. Mouret contributed equallyto this work). [pdf] [url] [source code] [video]

Reset-free Trial-and-Error Learning for Robot Damage Recovery (Robotics and Autonomous Systems, 2017)¶

K. Chatzilygeroudis, V. Vassiliades, J.-B Mouret (2017). Reset-free Trial-and-Error Learning for Robot Damage Recovery. Robotics and Autonomous Systems. 1-19. Elsevier. [doi] [pdf] [url] [source code] [video]

Trial-and-Error Learning of Repulsors for Humanoid QP-based Whole-Body Control (IEEE Humanoids 2017)¶

Spitz J, Bouyarmane K, Ivaldi S, Mouret J.-B. (2017) Trial-and-Error Learning of Repulsors for Humanoid QP-based Whole-Body Control. Proc. of IEEE Humanoids. [pdf]

Black-box Data-efficient Policy Search for Robotics (Black-DROPS) (IEEE IROS 2017)¶

Chatzilygeroudis K., Rama R., Kaushik R., Goepp D., Vassiliades V., and Mouret J-B. (2017). Black-box Data-efficient Policy Search for Robotics. Proc. of IEEE IROS. [pdf] [github (source code)]

Robots that can adapt like animals (Nature, 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). [pdf]

Supplementary Video S2 for “Robots that can adapt like animals” (Cully, Clune, Tarapore and Mouret, Nature, 2015).

In the behavior-performance map 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.

The Creadapt Robot (6-legged hybrid)¶

Reference: J.-M Jehanno, A. Cully, C. Grand, J.-B Mouret (2014). Design of a Wheel-Legged Hexapod Robot for Creative Adaptation. CLAWAR 17th International Conference on Climbing and Walking Robots. 267-276. [pdf]