Search Results

The unscented Kalman filter (UKF) is applied to estimate the real vehicle velocity. The velocity estimation algorithm uses lateral acceleration, longitudinal acceleration and yaw rate as inputs. The non-linear vehicle model and Dugoff tire model are built as the estimation model of UKF. Some parameters of Dugoff tire model and vehicle, which can't be measured directly, are identified by the particle swarm optimization (PSO). For the purpose of evaluating the algorithm, the estimation values of UKF are compared with measurements of the Inertial and GPS Navigation system. Besides, the real time property of UKF is tested by xPC Target, which is a real-time software environment from MathWorks. The result of the real vehicle experiment demonstrates the availability of the UKF and PSO in vehicle velocity estimation.

Vehicle pose estimation is a key technology for autonomous vehicles and a prerequisite for path planning and vehicle control. Visual localization has gradually attracted extensive attention from academia and industry due to its low cost and rich semantic information. However, the incremental calculation principle of the odometry inevitably leads to the accumulation of localization error with the travel distance. To solve this problem, we propose a position correction algorithm based on lightweight landmark map, and further compensate the localization error by analyzing the error characteristics. The proposed algorithm takes the stop lines on the road as landmarks, and pairs bag-of-word vectors with the positions of the corresponding landmarks. Once landmarks in the map are encountered and successfully associated, the position of the landmarks can be exploited to effectively reduce the drift of the odometry. We also present a reliable landmark map construction method.