题名: |
Learning Mobility: Adaptive Control Algorithms for the Novel Unmanned Ground Vehicle (NUGV) |
作者: |
Blackburn, Mike; |
关键词: |
LEARNING, REMOTELY PILOTED VEHICLES, ALGORITHMS, MOBILITY, ADAPTIVE CONTROL SYSTEMS, ROBOTS, TERRAIN, UNMANNED, GROUND VEHICLES. |
摘要: |
Mobility is a serious limiting factor in the usefulness of unmanned ground vehicles, This paper contains a description of our approach to develop control algorithms for the Novel Unmanned Ground Vehicle (NUGV) to address this problem. The NUGV is a six- degree-of-freedom, sensor-rich small mobile robot designed to demonstrate auto-learning capabilities for the improvement of mobility through variegated terrain. The learning processes we plan to implement are composed of classical and operant conditionings of novel responses built upon pre-defined fixed action patterns. The fixed action patterns will be in turn modulated by pre-defined low-level reactive behaviors that, as unconditioned responses, should continuously serve to maintain the viability of the robot during the activations of the fixed action patterns and of the higher-order (conditioned) behaviors. The sensors of the internal environment that govern the low-level reactive behaviors also serve as the criteria for operant conditioning. Using this adaptive controller, the NUGV should learn to negotiate difficult obstacles, and to protect itself from collisions and falls. |
总页数: |
54 |
报告类型: |
科技报告 |