Goal directed multi-finger manipulation: Control policies and analysis

@article{Andrews2013GoalDM,
  title={Goal directed multi-finger manipulation: Control policies and analysis},
  author={S. Andrews and P. Kry},
  journal={Comput. Graph.},
  year={2013},
  volume={37},
  pages={830-839}
}
We present a method for one-handed, task-based manipulation of objects. Our approach uses a mid-level, multi-phase approach to organize the problem into three phases. This provides an appropriate control strategy for each phase and results in cyclic finger motions that, together, accomplish the task. The exact trajectory of the object is never specified since the goal is defined by the final orientation and position of the object. All motion is physically based and guided by a control policy… Expand
Relaxed-Rigidity Constraints: In-Grasp Manipulation using Purely Kinematic Trajectory Optimization
Applications of machine learning in sensorimotor control
Towards learning hierarchical skills for multi-phase manipulation tasks
A Comparison of Action Spaces for Learning Manipulation Tasks
Real-Time Finger Gaits Planning for Dexterous Manipulation
Deep Dynamics Models for Learning Dexterous Manipulation
Real-time robust finger gaits planning under object shape and dynamics uncertainties
State-Only Imitation Learning for Dexterous Manipulation
...
1
2
3
4
...

References

SHOWING 1-10 OF 27 REFERENCES
Policies for Goal Directed Multi-Finger Manipulation
Contact-invariant optimization for hand manipulation
Dextrous manipulation from a grasping pose
  • C. Liu
  • Computer Science
  • SIGGRAPH 2009
  • 2009
Multi-modal Motion Planning for a Humanoid Robot Manipulation Task
Robust finger gaits from closed-loop controllers
  • M. Huber, R. Grupen
  • Engineering, Computer Science
  • IEEE/RSJ International Conference on Intelligent Robots and Systems
  • 2002
Synthesis of detailed hand manipulations using contact sampling
Generalization of human grasping for multi-fingered robot hands
Physically based grasping control from example
SIMBICON: simple biped locomotion control
...
1
2
3
...