Dogged Learning for Robots

Grollman, Daniel H.; Jenkins, Odest Chadwicke

doi:10.1109/robot.2007.363692

Cited by 86 publications

(81 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chernova et al use confidence estimation to train multiple robots individually and rely on emergent multirobot behavior to accomplish the task [5,6]. A similar approach was used to train Sony AIBO robots to play soccer [4,11,12].…”

Section: Related Workmentioning

confidence: 99%

Real-Time Training of Team Soccer Behaviors

Sullivan

Luke

2013

RoboCup 2012: Robot Soccer World Cup XVI

View full text Add to dashboard Cite

Abstract. Training robot or agent behaviors by example is an attractive alternative to directly coding them. However training complex behaviors can be challenging, particularly when it involves interactive behaviors involving multiple agents. We present a novel hierarchical learning from demonstration system which can be used to train both single-agent and scalable cooperative multiagent behaviors. The methodology applies manual task decomposition to break the complex training problem into simpler parts, then solves the problem by iteratively training each part. We discuss our application of this method to multiagent problems in the humanoid RoboCup competition, and apply the technique to the keepaway soccer problem in the RoboCup Soccer Simulator.

show abstract

Section: Related Workmentioning

confidence: 99%

Real-Time Training of Team Soccer Behaviors

Sullivan

Luke

2013

RoboCup 2012: Robot Soccer World Cup XVI

View full text Add to dashboard Cite

show abstract

“…The Hidden Markov model (HMM) is used for recognition and regeneration of human motion across various demonstrations [39,40], and to teach a robot to perform assembly tasks [41]. Locally Weighted Projection Regression (LWPR) is used to approximate the dynamic model of a robot arm for computed torque control [42,32], for teaching a robot to perform basic soccer skills [43], and is also applied for real-time motion learning for a humanoid robot [32]. Statistical approaches that find a locally optimal model to represent the demonstrations by maximizing the likelihood, are also possible.…”

Section: Machine Learning Techniques For Modeling Robotic Tasksmentioning

confidence: 99%

Estimating the non-linear dynamics of free-flying objects

Kim

Billard

2012

Robotics and Autonomous Systems

View full text Add to dashboard Cite

a b s t r a c tThis paper develops a model-free method to estimate the dynamics of free-flying objects. We take a realistic perspective to the problem and investigate tracking accurately and very rapidly the trajectory and orientation of an object so as to catch it in flight. We consider the dynamics of complex objects where the grasping point is not located at the center of mass.To achieve this, a density estimate of the translational and rotational velocity is built based on the trajectories of various examples. We contrast the performance of six non-linear regression methods (Support Vector Regression (SVR) with Radial Basis Function (RBF) kernel, SVR with polynomial kernel, Gaussian Mixture Regression (GMR), Echo State Network (ESN), Genetic Programming (GP) and Locally Weighted Projection Regression (LWPR)) in terms of precision of recall, computational cost and sensitivity to choice of hyper-parameters. We validate the approach for real-time motion tracking of 5 daily life objects with complex dynamics (a ball, a fully-filled bottle, a half-filled bottle, a hammer and a pingpong racket). To enable real-time tracking, the estimated model of the object's dynamics is coupled with an Extended Kalman Filter for robustness against noisy sensing.

show abstract

“…For example, execution experience is used to update state transition models [1] and reward-determined state values [13]. Other approaches provide more demonstration data, driven by learner requests for more data [7,8] as well as more teacher-initiated demonstrations [6].…”

Section: Learning From Demonstrationmentioning

confidence: 99%

Learning Mobile Robot Motion Control from Demonstrated Primitives and Human Feedback

Argall

Browning

Veloso

2011

Springer Tracts in Advanced Robotics

View full text Add to dashboard Cite

Task demonstration is one effective technique for developing robot motion control policies. As tasks become more complex, however, demonstration can become more difficult. In this work we introduce a technique that uses corrective human feedback to build a policy able to perform an undemonstrated task from simpler policies learned from demonstration. Our algorithm first evaluates and corrects the execution of motion primitive policies learned from demonstration. The algorithm next corrects and enables the execution of a larger task built from these primitives. Within a simulated robot motion control domain, we validate that a policy for an undemonstrated task is successfully built from motion primitives learned from demonstration under our approach. We show feedback to both aid and enable policy development, improving policy performance in success, speed and efficiency.

show abstract

Dogged Learning for Robots

Cited by 86 publications

References 8 publications

Real-Time Training of Team Soccer Behaviors

Real-Time Training of Team Soccer Behaviors

Estimating the non-linear dynamics of free-flying objects

Learning Mobile Robot Motion Control from Demonstrated Primitives and Human Feedback

Contact Info

Product

Resources

About