Search

In practical applications, how to use the complementary strengths of the direct and the feature-based methods for effective fusion may be the main challenge of simultaneous localization and mapping (SLAM). To solve this challenge, we propose the DO-SLAM, a novel fast and accurate semi-direct visual SLAM framework, which can maintain the direct method’s fast performance and the high precision and loop closure capability of the feature-based method. The direct method is used as the first half of the DO-SLAM to track the camera pose rapidly and robustly. The feature-based method is used as the second half of the DO-SLAM to refine the keyframe poses, perform loop closures, and build a globally consistent, long-term, sparse feature map that can be reused. The proposed pipeline fuses direct odometry and feature-based SLAM to perform three levels of parallel optimizations: (1) In the direct method module, the keyframe poses are estimated by minimizing the photometric error, (2) In the feature-based module, using the poses calculated by the inter-frame matching to correct and fuse the poses calculated by the direct method module as the initial poses, and the initial poses are optimized by the motion-only bundle adjustment, and (3) A pose graph optimization is used to achieve global map consistency in the presence of loop closures. Experimental evaluation on two benchmark datasets demonstrates that the proposed approach achieves higher accuracy and robustness on motion estimation compared to the other state-of-the-art methods.

Traffic vehicle behavior prediction is a necessary prerequisite for intelligent vehicle behavior decision and trajectory planning. The behaviors of vehicles are deeply interactive. In order to reasonably predict the future behavior of traffic vehicles, based on the Game theory, this paper designs the behavior prediction framework of traffic vehicles, and establishes the GMM(Gaussian Mixture Model)-HMM(Hidden Markov Model) behavior recognition model. Then, the revenue function is designed to model the driver's intent by calculating the vehicle's front running space, collision risk and comfort loss under each scenario. And the NGSIM dataset is used to train the parameters in the GMM-HMM model and those in the revenue function. Finally, two groups of experiments are designed to compare this method with the traditional method. The experimental results show that the proposed method can predict the future behavior of traffic vehicles earlier, and can also well reflect the interaction process of vehicle behavior, and has better robustness.