In the field of autonomous driving, relying solely on environmental information captured by single vehicle’s LiDAR often falls short of perception requirements in complex scenarios. Adopting a vehicle-infrastructure cooperation approach can effectively address information limitations. Therefore, the development of an algorithm that can register heterogeneous LiDAR point clouds is crucial. This paper proposes a vehicle-infrastructure cooperative heterogeneous point cloud registration network (TEA-IHPCR) based on temporal augmented information and rotation invariance. By capturing temporal augmented information between continuous frames of point clouds, data augmentation is performed on the point cloud data from both vehicle and infrastructure sides, mitigating issues of poor heterogeneous point cloud registration caused by perspective differences. The rotation invariance property can address the issue of aligning coordinate systems between the vehicle and infrastructure sides that have not been collaboratively calibrated. Simultaneously, the use of a local-level encoder capable of extracting point cloud features with rotation invariance, combined with a global-level attention mechanism that can learn cross-frame features, improves the model’s performance in low-overlap rate point cloud registration. The experiments were conducted on a vehicle-infrastructure collaborative dataset while the results demonstrate the effectiveness of the proposed module in the network, as well as its superiority and efficiency compared to other networks.

In order to solve the problem of autonomous vehicles driving safely on the road while searching for optimal paths to avoid traffic congestion and obstruction, this paper establishes an optimal path planning model based on image feature extraction. The model consists of four parts: the selection of key turning points, interpolation between turning points, definition of the evaluation function, and global optimal path search. First, based on the map information provided by the network, an image feature detection algorithm was proposed, and the key turning points of the map route were selected and stored in an open table. Then, based on mechanical analysis theory, the cubic interpolation between two key turning points of the optimal path was defined. This allows the car to drive along a continuous curve with a certain arc radius, enabling it to drive smoothly, effectively avoid obstacles, and ensure safety. Then, an evaluation function is defined as needed, and different evaluation functions are specified for different road sections to avoid excessive local deviations in planning and to reduce the impact of known obstacles on the path. Finally, the cost of the search path is calculated based on the evaluation function. According to the principle of minimum cost, a globally optimal heuristic search algorithm is proposed to find the globally optimal path. Experimental results show that the proposed global optimal path planning algorithm has excellent performance, with an average accuracy of 96.71% and a search speed of 2.78 ms. The model not only provides accurate path planning and fast path selection capabilities but also has strong robustness against interference.

Robotaxis are emerging as a key component of urban transportation. However, most current robotaxis rely on preset pick-up points, which cluster robotaxi activity and intensify local traffic congestion, increase deadheading and detour distances, extend roadway occupancy, and raise operating costs. GNSS-based localization may be unreliable especially in urban area. Generally, human drivers can communicate with passengers through text/voice interactions to accurately locate and reach the human’s location. How to align the robotaxi’s visual recognition results with human text/voice description is the key challenge. Therefore, we propose a comprehensive framework, including its architecture, requirment, opertional logic, workflow, to enhance the passenger-robotaxi interaction for accurate passenger pick-up without preset pick-up points. In this framework, the key algorithm is VLMIdentification, a realtime human identification model based on LVLM. VLMIdentification comprises three modules: i) Human Input Processing, which extracts textual features from passenger text/voice and converts human-centric descriptions into third-person, robotaxi-centric attributes; ii)Candidate Searching, which couples conventional detectors with an LVLM to adapt detection thresholds to scene complexity and to translate detections into textual descriptors; and iii) Human Identification, which performs matching between the processed passenger description and candidates to locate the correct human. We defined the human identification with multimodal task, proposed evaluation metrics, and built a new HID (Human Identification with Description) dataset based on existing autonomous driving datasets. Experimental results demonstrate that VLMIdentification outperforms baseline in comprehensive metrics and retains robust, performance under adverse environment and cross-scenario generalization tests, thereby confirming its generalization and robustness. Code is available at https://github.com/fanwu66/VLMIdentification