Abstract | ||
---|---|---|
Functional locomotion requires continuous modulation of coordination within and between legs to flexibly accommodate demands of real-word environments. In this context, dynamic movement primitives (DMP) is a powerful tool for motion planning based on demonstrations, being used as a compact policy representation well-suited for robot learning. In this work, we study on-line adaptation of robot biped locomotion patterns when employing DMP as trajectory representations. Here, the adaptation of learned walking movements is obtained from a single demonstration. The goal is to demonstrate and evaluate how new movements can be generated by simply modifying the parameters of rhythmic DMP learned in task space. The formulation in task space allows recreating new movements such that the DMP's parameters directly relate to task variables, such as step length, hip height, foot clearance and forward velocity. Several experiments are conducted using the V-REP robotics simulator, including the adaptation of the robot's gait pattern to irregularities on the ground surface and stepping over obstacles. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/ICARSC.2015.9 | ICARSC |
Keywords | Field | DocType |
collision avoidance,digital simulation,gait analysis,learning (artificial intelligence),legged locomotion,motion control,velocity control,dmp,v-rep robotics simulator,compact policy representation,dynamic movement primitives,foot clearance,forward velocity,functional locomotion,ground surface,hip height,learned walking movements,motion planning,obstacles,robot biped locomotion patterns,robot gait pattern,robot learning,robot locomotion patterns adaptation,step length,task space,task variables,biped locomotion,motor primitives,movement adaptation,single demonstration,modulation,trajectory,robot kinematics,foot,learning artificial intelligence | Motion planning,Robot learning,Computer vision,Motion control,Computer science,Simulation,Robot kinematics,Robotics simulator,Robot locomotion,Gait analysis,Artificial intelligence,Robot | Conference |
ISSN | Citations | PageRank |
2573-9360 | 1 | 0.36 |
References | Authors | |
11 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
José Rosado | 1 | 9 | 2.03 |
Filipe M. T. Silva | 2 | 65 | 14.07 |
Vítor M. F. Santos | 3 | 95 | 21.33 |