Abstract | ||
---|---|---|
Many human skills can be described in terms of performing a set of prioritised tasks. While a number of tools have become available that recover the underlying control policy from constrained movements, few have explicitly considered learning how constraints should be imposed in order to perform the control policy. In this paper, a method for learning the self-imposed constraints present in movement observations is proposed. The problem is formulated into the operational space control framework, where the goal is to estimate the constraint matrix and its null space projection that decompose the task space and any redundant degrees of freedom. The proposed method requires no prior knowledge about either the dimensionality of the constraints nor the underlying control policies. The techniques are evaluated on a simulated three degree-of-freedom arm and on the AR10 humanoid hand. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/ICRA.2017.7989039 | 2017 IEEE International Conference on Robotics and Automation (ICRA) |
Keywords | Field | DocType |
learning task constraints,operational space formulation,human skills,control policy,self-imposed constraints learning,operational space control,constraint matrix,three degree-of-freedom arm,AR10 humanoid hand | Kernel (linear algebra),Mathematical optimization,Control theory,Curse of dimensionality,Redundancy (engineering),Aerospace electronics,Linear programming,Mathematics,Constraint matrix,Operational space control | Conference |
Volume | Issue | ISBN |
2017 | 1 | 978-1-5090-4634-8 |
Citations | PageRank | References |
3 | 0.41 | 7 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hsiu-Chin Lin | 1 | 3 | 0.75 |
Prabhakar Ray | 2 | 3 | 0.75 |
Matthew Howard | 3 | 6 | 2.53 |