Robotic grasping of unknown objects: A knowledge-based approach

Conference · Wed Oct 31 23:00:00 EST 1990

OSTI ID:714959

Stansfield, S A ^[1]

---

1. Sandia National Labs., Albuquerque, NM (United States)

In this paper, the authors demonstrate a general-purpose robotic grasping system for use in unstructured environments. Using computer vision and a compact set of heuristics, the system automatically generates the robot arm and hand motions required for grasping an unmodeled object. The utility of such a system is most evident in environments where the robot will have to grasp and manipulate a variety of unknown objects, but where many of the manipulation tasks may be relatively simple. Examples of such domains are planetary exploration and astronaut assistance, undersea salvage and rescue, and nuclear waste site clean-up. This work implements a two-stage model of grasping: stage one is an orientation of the hand and wrist and a ballistic reach toward the object; stage two is hand preshaping and adjustment. Visual features are first extracted from the unmodeled object. These features and their relations are used by an expert system to generate a set of valid reach/grasps for the object. These grasps are then used in driving the robot hand and arm to bring the fingers into contact with the object in the desired configuration. Experimental results are presented to illustrate the functioning of the system.

• Research Organization: General Electric Co., Largo, FL (United States). Neutron Devices Dept.
• DOE Contract Number: AC04-76DP00656
• OSTI ID: 714959
• Report Number(s): GEPP-CP--1222; CONF-9004263--; ON: TI91020218
• Country of Publication: United States
• Language: English

Related Subjects

05
42 ENGINEERING
99 GENERAL AND MISCELLANEOUS
ARMS
ARTIFICIAL INTELLIGENCE
ASTRONAUTS
AUTOMATION
CONTROL
EXPERT SYSTEMS
EXPLORATION
HANDS
IMAGE PROCESSING
KNOWLEDGE BASE
MANIPULATORS
MATERIALS HANDLING EQUIPMENT
MATHEMATICAL MODELS
NAVIGATION
PLANETS
RADIOACTIVE WASTE FACILITIES
RADIOACTIVE WASTE PROCESSING
RESCUE OPERATIONS
ROBOTS
TRAJECTORIES