Work

Emergent Control and Planning in an Autonomous Vehicle

Year: 1993

Type: article

Abstract: We use a connectionist network trained with rein-\nforcement to control both an autonomous robot ve-\nhicle and a simulated robot. We show that given\nappropriate sensory data and architectural struc-\nture, a network can learn to control the robot for\na simple navigation problem. We then investigate a\nmore complex goal-based problem and examine the\nplan-like behavior that emerges.

Source: Scholarship, Research, and Creative Work at Bryn Mawr College (Bryn Mawr College)

Authors: Lisa Meeden, Gary A. McGraw, Douglas Blank

Language: English

Topic: Reinforcement Learning in Robotics

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W1567800133

FWCI: 0.429

Cites:

Cited by: 24

Related to: 10