Autonomous Learning of Stable Quadruped Locomotion

Saggar, Manish; D'Silva, Thomas; Kohl, Nate; Stone, Peter

doi:10.1007/978-3-540-74024-7_9

Cited by 22 publications

(11 citation statements)

References 9 publications

(15 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is a very important slow statically stable gait with three legs in ground contact, suitable for postural control and therefore required to deal with movement in uneven terrain. In current works [2], [14], [9] the robot configuration is the one required to achieve higher velocities: the robot knees are completely folded and use a trot gait locomotion. Therefore, differently from current literature, in this work the aim is not to achieve the highest possible velocity in any gait, but rather to achieve the highest velocity for a slow crawl gait, which has to respect a given duty factor and certain phase relationships.…”

Section: Introductionmentioning

confidence: 99%

Multi-objective parameter CPG optimization for gait generation of a quadruped robot considering behavioral diversity

Oliveira

Santos

Costa

et al. 2011

2011 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

This paper presents a gait multi-objective optimization system that combines bio-inspired Central Patterns Generators (CPGs) and a multi-objective evolutionary algorithm. CPGs are modeled as autonomous differential equations, that generate the necessary limb movement to perform the required walking gait. In order to optimize the walking gait, four conflicting objectives are considered, simultaneously: minimize the body vibration, maximize the velocity, maximize the wide stability margin and maximize the behavioral diversity. The results of NSGA-II for this multi-objective problem are discussed. The effect of the inclusion of a behavioral diversity objective in the system is also studied in terms of the walking gait achieved. The experimental results show the effectiveness of this multi-objective approach. The several walking gait solutions obtained correspond to different trade-off between the objectives.

show abstract

Section: Introductionmentioning

confidence: 99%

Multi-objective parameter CPG optimization for gait generation of a quadruped robot considering behavioral diversity

Oliveira

Santos

Costa

et al. 2011

2011 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

show abstract

“…Saggar [6] presents results on using the policy gradient algorithm to learn a stable, fast gait. Both are fully implemented and tested on the Aibo robot platform.…”

Section: Different Approachesmentioning

confidence: 99%

Robot self-preservation and adaptation to user preferences in game play, a preliminary study

Castro‐González

Amirabdollahian

Polani

et al. 2011

2011 IEEE International Conference on Robotics and Biomimetics

View full text Add to dashboard Cite

It is expected that in a near future, personal robots will be endowed with enough autonomy to function and live in an individual's home. This is while commercial robots are designed with default configuration and factory settings which may often be different to an individual's operating preferences. This paper presents how reinforcement learning is applied and utilised towards personalisation of a robot's behaviour. Twolevel reinforcement learning has been implemented: first level is in charge of energy autonomy, i.e. how to survive, and second level is involved in adapting robot's behaviour to user's preferences. In both levels Q-learning algorithm has been applied. First level actions have been learnt in a simulated environment and then the results have been transferred to the real robot. Second level has been fully implemented in the real robot and learnt by human-robot interaction. Finally, experiments showing the performance of the system are presented.

show abstract

“…Second, a equal amount of literature has applied machine learning to a robot's kinematics, dynamics, or structure. The lion's share of this work involves gait development (such as [19,18]), with some work on kicking [6,32], head actuation [5] and omnidirectional velocity control [17]. Third, about sixteen papers have concerned themselves with learning higher-level behaviors (for example [26,28]).…”

Section: Machine Learning At Robocupmentioning

confidence: 99%

Towards Rapid Multi-robot Learning from Demonstration at the RoboCup Competition

Freelan

Wicke

Sullivan

et al. 2015

RoboCup 2014: Robot World Cup XVIII

View full text Add to dashboard Cite

Abstract. We describe our previous and current efforts towards achieving an unusual personal RoboCup goal: to train a full team of robots directly through demonstration, on the field of play at the RoboCup venue, how to collaboratively play soccer, and then use this trained team in the competition itself. Using our method, HiTAB, we can train teams of collaborative agents via demonstration to perform nontrivial joint behaviors in the form of hierarchical finite-state automata. We discuss HiTAB, our previous efforts in using it in RoboCup 2011 and 2012, recent experimental work, and our current efforts for 2014, then suggest a new RoboCup Technical Challenge problem in learning from demonstration.Imagine that you are at an unfamiliar disaster site with a team of robots, and are faced with a previously unseen task for them to do. The robots have only rudimentary but useful utility behaviors implemented. You are not a programmer. Without coding them, you have only a few hours to get your robots doing useful collaborative work in this new environment. How would you do this?Our interest lies in rapid, real-time multi-robot training from demonstration. Here a single human trainer teaches a team of robots, via teleoperation, how to collectively perform tasks in previously unforeseen environments. This is difficult for two reasons. First, nontrivial behaviors can present a high-dimensional space to learn, yet one can only provide a few samples, as online training samples are costly to collect. This is a worst case for the so-called "curse of dimensionality". Second, when training multiple interactive robots, even if you can quantify the emergent macro-level group behavior you wish to achieve, in order to do learning, each agent needs to know the micro-level behavior he is being asked to do. One may have a micro→macro function (a simulator), but it is unlikely that one has the inverse macro→micro function, resulting in what we call the "multiagent inverse problem". These two challenges mean that real-time multi-robot learning from demonstration has proven very difficult and has a very sparse literature.Over the past several years we have participated in the Kid-Size Humanoid League with a single objective: to successfully do a personal RoboCup-style technical challenge of our own invention, independent of those offered at RoboCup: can we train multiple generic robots, through demonstration on the field, how to play collaborative soccer at RoboCup solely within the preparatory time prior to the competition itself ?

show abstract

Autonomous Learning of Stable Quadruped Locomotion

Cited by 22 publications

References 9 publications

Multi-objective parameter CPG optimization for gait generation of a quadruped robot considering behavioral diversity

Multi-objective parameter CPG optimization for gait generation of a quadruped robot considering behavioral diversity

Robot self-preservation and adaptation to user preferences in game play, a preliminary study

Towards Rapid Multi-robot Learning from Demonstration at the RoboCup Competition

Contact Info

Product

Resources

About