Earth-moving is a common activity at mines, construction sites, hazardous waste cleanup locations, and road works. Expensive and sophisticated machines such as wheel loaders are used for earth-moving. This book presents a robotic control approach to the computer control of wheel-loader-type excavators. The unpredictable and dynamic rock excavation environment poses challenges for the design of the real time control algorithm. The control method developed here is based on the analysis of human operators' performance; it applies neural networks, fuzzy logic and finite state machines to embody human excavation strategies for on-line bucket digging trajectory design. A behavior-based control architecture organizes operation of the modules to achieve quick system response. Extensive experiments have been performed to demonstrate the diggability of the algorithm in various difficult-to-excavate environments.

Earth-moving is a common activity at mines, construction sites, hazardous waste cleanup locations, and road works. Expensive and sophisticated machines such as wheel loaders are used for earth-moving. This book presents a robotic control approach to the computer control of wheel-loader-type excavators. The unpredictable and dynamic rock excavation environment poses challenges for the design of the real time control algorithm. The control method developed here is based on the analysis of human operators' performance; it applies neural networks, fuzzy logic and finite state machines to embody human excavation strategies for on-line bucket digging trajectory design. A behavior-based control architecture organizes operation of the modules to achieve quick system response. Extensive experiments have been performed to demonstrate the diggability of the algorithm in various difficult-to-excavate environments.

Earth-moving is a common activity at mines, construction sites, hazardous waste cleanup locations, and road works. Expensive and sophisticated machines such as wheel loaders are used for earth-moving. This book presents a robotic control approach to the computer control of wheel-loader-type excavators. The unpredictable and dynamic rock excavation environment poses challenges for the design of the real time control algorithm. The control method developed here is based on the analysis of human operators' performance; it applies neural networks, fuzzy logic and finite state machines to embody human excavation strategies for on-line bucket digging trajectory design. A behavior-based control architecture organizes operation of the modules to achieve quick system response. Extensive experiments have been performed to demonstrate the diggability of the algorithm in various difficult-to-excavate environments.