UMass Research Infrastructure:
Sensorimotor Development in Humans and Machines

Grasping as a Haptic Control Problem

Platt, Jr., R., Fagg, A. H., Grupen, R. A. (2004), Manipulation Gaits: Sequences of Grasp Control Tasks, to Appear in the International Conference on Robotics and Automation (ICRA'04) Platt, Jr., R., Fagg, A. H., Grupen, R. A. (2003), Extending Fingertip Grasping to Whole Body Grasping, Proceedings of International Conference on Robotics and Automation (ICRA'03), pp. 2677-2682 Platt, Jr., R., Fagg, A. H., Grupen, R. A. (2002), Nullspace Composition of Control Laws for Grasping, Proceedings of the International Conference on Intelligent Robots and Systems (IROS'02), Electronically Published

Movies

Grasping Cylinders: Top Approach		grasp_top.mov grasp_top.mp4 grasp_top.avi
Grasping Cylinders: Side Approach 2 fingers form a virtual finger		grasp_peanutbutter.mov grasp_peanutbutter.mp4 grasp_peanutbutter.avi
Whole Body Grasping		wbg_move_left.mov wbg_move_left.mp4 wbg_move_left.avi
Learning Grasp Location Affordances		grasp_afford.mov grasp_afford.mp4 grasp_afford.avi

Learning to Prospectively Select Grasps

Inspired by our infant development work, we have applied a reinforcement learning technique to the problem of discovering an appropriate sequence of grasp and place actions. Rather than starting with a model of which grasp was appropriate for a given final object configuration, the robot learned through interaction with the environment to select a grip in anticipation of how the grasped object was to be used in future actions. The behavior exhibited through the learning process by the robot demonstrated qualitative similarities to what one sees in the development of grip selection by children in a similar task.

McCarty, M. E. and Clifton, R. K. and Collard, R. R. (1999), Problem solving in infancy: The emergence of an action plan in Developmental Psychology, 35(4):1091-1101 McCarty, M. E., Clifton, R. K., & Collard, R. R. (2001). The beginnings of tool use by infants and toddlers in Infancy, 2:233-256. Wheeler, D. S., Fagg, A. H., Grupen, R. A. (2002), Learning Prospective Pick and Place Behavior, Proceedings of the International Conference on Development and Learning (ICDL'02), Electronically Published

Staged learning

The robot is presented with a jar in one of two orientations. The task is to place the jar vertically with the top facing upwards. Through the course of interacting with the jar, the robot must discover 1) the sequence of actions that will accomplish the task and 2) the visual features that will allow the robot to select the appropriate sequence for a given situation. The robot is only told when the task is completed properly.

The following movies show individual trials during the learning process. In the first few trials, the robot is presented with the jar in only one orientation; this leads to the development of a "reflexive" response of reaching with the left arm (independent of the visual inputs). In the remaining trials, the jar is oriented randomly, requiring the robot to integrate the visual inputs into its decision making process.

Left Presentations Only: Prior to Learning		applesauce3-easy-other-final.mov applesauce3-easy-other-final.mp4 applesauce3-easy-other-final.avi
Left Presentation Only: Strategy After Learning		applesauce1-easy-final.mov applesauce1-easy-final.mp4 applesauce1-easy-final.avi
Both Orientations Presented: Before Learning		applesauce4-hard-late-final.mov applesauce4-hard-late-final.mp4 applesauce4-hard-late-final.avi
Both Orientations Presented: During Learning		applesauce8-hard-early-final.mov applesauce8-hard-early-final.mp4 applesauce8-hard-early-final.avi
Both Orientations Presented: After Learning		applesauce7-hard-optimal-final.mov applesauce7-hard-optimal-final.mp4 applesauce7-hard-optimal-final.avi

Learning Task Sequences from Demonstration

The remote teleoperation of robots is one of the dominant modes of robot control in applications involving hazardous environments, including space. Here, a user is equipped with an interface that conveys the sensory information being collected by the robot and allows the user to command the robot's actions. The difficulty with this form of interface is the degree of fatigue that is experienced by the user, often within a short period of time. To alleviate this problem, we are working with our colleagues at the NASA Johnson Space Center to develop user interfaces that anticipate the actions of the user, allowing the robot to aid in the partial performance of the task, or even to learn how to perform entire tasks autonomously. Our approach is to use our automatic control techniques to aid in the recognition of the user's actions. Prior to the user demonstration, the control system enumerates the different grasping actions that can be used for each object in the workspace (essentially, the robot "imagines" what it would feel like to pick up every object). The movements produced by the user are then compared against each of these imagined actions. The one action that best matches the user-driven movement is considered to be the explanation of that movement. Using this technique, we are able to recognize entire sequences of actions.

Movies

Demonstration of a sequence by a user through a teleoperation interface. In this example, the extracted sequence is: pick up the blue ball; place it on the pink target, pick up the yellow ball, and place it on the orange target.		sequence_learn_v2_demo.mov sequence_learn_v2_demo.mp4 sequence_learn_v2_demo.avi sequence_learn_v2_demo_small.avi
Automated replay of the same action sequence in a novel situation. Note that the movements are smoother and are executed more quickly than when the user is in control.		sequence_learn_v2_D.mov sequence_learn_v2_D.mp4 sequence_learn_v2_D.avi sequence_learn_v2_D_small.avi

Last modified: Fri Mar 26 10:51:00 2004