Determining control characteristics for an autonomous driving vehicle

    公开(公告)号:US10272924B2

    公开(公告)日:2019-04-30

    申请号:US15383843

    申请日:2016-12-19

    申请人: Baidu USA LLC

    摘要: Described is a system and method that provides the ability for an autonomous driving vehicle (ADV) to determine (or estimate) one or more control characteristics for the ADV. In order to determine these control characteristics, the system may perform one or more driving maneuvers such as an acceleration or deceleration maneuver, and a constant velocity maneuver. By performing these maneuvers using various known forces, the system may then perform various calculations to obtain one or more unknown characteristics. For example, the system may determine as estimated mass of the ADV, and as a result, adjust (or tune) various controls of the ADV based on the estimated mass.

    Data-based control error detection and parameter compensation system

    公开(公告)号:US10474157B2

    公开(公告)日:2019-11-12

    申请号:US15615378

    申请日:2017-06-06

    申请人: Baidu USA LLC

    摘要: State of an autonomous driving vehicle (ADV) is measured and stored for a location and speed of the ADV. Later, the state of the ADV is measured for the location and speed corresponding to a previously stored state of the ADV at the same location and speed. Fields of the measured stored states of the ADV are compared. If one or more differences between the measured and stored ADV states exceeds a threshold, then one or more control input parameters of the ADV is adjusted, such as steering, braking, or throttle. Differences may be attributable to road conditions or to state of servicing of the ADV. Differences between measured and stored states of the ADV can be passed to a service module. Service module can access crowd sourced data to determine whether one or more control input parameters for a driving state of one or more ADVs should be updated.