Localization is critical for automated vehicles as it provides essential position, velocity, and heading angle information to perform object tracking, trajectory prediction, motion planning, and control. However, model/environmental uncertainties (including road friction) and noises in sensor measurements have a significant effect on the accuracy of the localization and vehicle state estimation, specially for perceptually degraded conditions. In this paper, an integrated localization method based on the fusion of an inertial dead reckoning model and 3D LiDAR-based map matching is proposed and experimentally verified in an urban environment with varying environmental conditions. Leveraging a global navigation satellite system (GNSS), inertial navigation system (INS), and 3D LiDAR point clouds, a novel light point cloud map generation method, which only keeps the necessary point clouds (i.e., buildings and roads regardless of vegetation varying with seasonal change), is proposed. Subsequently, based on the onboard sensors and the pre-built light point cloud map, a dead reckoning model is derived and integrated with the normal distribution transformation (NDT) based map matching algorithm by an error-state-constrained Kalman filter to limit the localization error. On top of the Kalman filter, the stability analysis of the estimator is presented. Finally, the performance of the algorithm is validated in real road experiments under various environmental conditions. Thorough experiments in winter and summer and associated results confirm the advantages of integrating the proposed light point cloud map generation with the dead reckoning model in terms of accuracy and reduced computational complexity.

Predicting object motion behaviour is a challenging but crucial task for safe decision making and path planning for autonomous vehicles. It is challenging in large part due to the uncertain, multi-modal, and practically intractable set of possible agent-agent and agent-space interactions, especially in urban driving settings. Models solely based on constant velocity or social force have an inherent bias and may lead to inaccurate predictions across the prediction horizon whereas purely data driven approaches suffer from a lack of holistic set of rules governing predictions. We tackle this problem by introducing MPC-PF: a novel potential field-based trajectory predictor that incorporates social interaction via agent-agent and agent-space considerations and is able to tradeoff between inherent model biases across the prediction horizon. Through evaluation on the Waymo Open Motion Dataset and a variety of other common urban driving scenarios, we show that our model is capable of achieving state-of-the-art performance while producing accurate predictions for both short and long term timesteps. We also demonstrate the significance of our model architecture through an ablation study.

A slip-aware localization framework is proposed for mobile robots experiencing wheel slip in dynamic environments. The framework fuses infrastructure-aided visual tracking data (via fisheye lenses) and proprioceptive sensory data from a skid-steer mobile robot to enhance accuracy and reduce variance of the estimated states. The slip-aware localization framework includes: the visual thread to detect and track the robot in the stereo image through computationally efficient 3D point cloud generation using a region of interest; and the ego motion thread which uses a slip-aware odometry mechanism to estimate the robot pose utilizing a motion model considering wheel slip. Covariance intersection is used to fuse the pose prediction (using proprioceptive data) and the visual thread, such that the updated estimate remains consistent. As confirmed by experiments on a skid-steer mobile robot, the designed localization framework addresses state estimation challenges for indoor/outdoor autonomous mobile robots which experience high-slip, uneven torque distribution at each wheel (by the motion planner), or occlusion when observed by an infrastructure-mounted camera. The proposed system is real-time capable and scalable to multiple robots and multiple environmental cameras.

The recent progress in machine learning has shifted the trends in artificial intelligence (AI) toward an overreliance on increasing amounts of data, computing power, and model parameters. These trends have resulted in success, but have also created a monolithic perspective for AI, increased the barriers to entry outside of large tech companies, and raised concerns about computational sustainability. Neurosymbolic AI is a growing area that promotes methodological heterogeneity and aims to push the frontiers of AI through affordable data and computing power.

Conventional visual navigation methods presume scene stability and encounter challenges due to moving objects in highly dynamic environments. We propose DynaNav-SVO, a stereo visual odometry (VO) framework, which semantically detects and constructs a region-of-interest (ROI) by focusing on a-priori urban fixed elements for reliable feature extraction and subsequently estimates vehicle pose. The outcome is a static map with minimal outliers and is used for state estimation in dynamic scenes and perceptually degraded conditions. This map enhances computational efficiency due to the reduced size of the new static mask (as confirmed in several experiments), compared to the existing visual simultaneous localization and mapping (vSLAM) solutions. To refine the estimated pose, a back-end module selects a moving horizon of frames, generates a covisibility graph for data association, and optimizes a structure-from-motion program using local bundle adjustment. Finally, the performance of the framework is experimentally evaluated using a test vehicle in highly-dynamic urban settings and under adverse weather conditions with degraded visual perception with varying sequence lengths. The experiments confirm excellent performance in terms of estimation accuracy and computational efficiency for autonomous navigation compared to existing vSLAM methods.

Predicting object motion behaviour is a challenging but crucial task for safe decision making and path planning for an autonomous vehicle. It is challenging in large part due to the uncertain, multi-modal, and practically intractable set of possible agent-agent and agent-space interactions, especially in urban driving settings. Models solely based on constant velocity or social force have an inherent bias and may lead to inaccurate predictions across the prediction horizon whereas purely data driven approaches suffer from a lack of a holistic set of rules governing predictions. We tackle this problem by introducing MPC-PF: a novel potential field-based trajectory predictor that incorporates social interaction and is able to tradeoff between inherent model biases across the prediction horizon. Through evaluation on a variety of common urban driving scenarios, we show that our model is capable of producing accurate predictions for both short and long term timesteps. We also demonstrate the significance of our model architecture through an ablation study.