发明授权
- 专利标题: Learning mechanism for autonomous trucks for mining and construction applications
-
申请号: US16679376申请日: 2019-11-11
-
公开(公告)号: US11644843B2公开(公告)日: 2023-05-09
- 发明人: Alberto Daniel Lacaze , Karl Nicholas Murphy
- 申请人: Robotic Research OpCo, LLC
- 申请人地址: US MD Clarksburg
- 专利权人: ROBOTIC RESEARCH OPCO, LLC
- 当前专利权人: ROBOTIC RESEARCH OPCO, LLC
- 当前专利权人地址: US MD Clarksburg
- 代理机构: RowanTree Law Group, PLLC
- 代理商 Frederick F. Rosenberger
- 主分类号: G05D1/02
- IPC分类号: G05D1/02 ; G05D1/00
摘要:
The invention simplifies the process of utilizing mmmg or construction trucks to automatically carry ore, dirt, or other matter from one location to another. Transportation of the dirt, ore, or matter is usually performed using trucks with loaders or excavators. The trucks then take the loads and deposit them in piles, which are then used for the next step of the mining or construction process. The invention uses a teach-and-follow process to establish the trajectories that these paths must follow. The present invention describes a system to record and execute trajectories for autonomous mining and construction trucks. This system comprises one or more sensors that can detect road features, a drive-by-wire kit installed onto the truck(s), a user interface that allows the operator to learn trajectories and “replay trajectories”, and a planning algorithm that creates trajectories which take the vehicle from a starting location to an ending location (final destination), while maintaining the vehicle inside of the allowed driving envelope. The invention allows the user to drive the truck along the desired route and have the truck automatically learn the route using features in the environment to localize. In future runs, the truck is able to automatically follow the learned route.
公开/授权文献
信息查询