In a complex off-road environment, due to the low bearing capacity of the soil and the uneven features of the terrain, generating a safe and effective global route for unmanned ground vehicles (UGVs) is critical for the success of their motion and mission. Most traditional global path planning methods simply take the shortest path length as the optimization objective, which makes it difficult to plan a feasible and safe route in complex off-road environments. To address this problem, this research proposes a global path planning method, which considers the influence of terrain factors and soil mechanics on UGV mobility. First, we established a high-resolution 3D terrain model with remote sensing elevation terrain data, land use and soil type distribution data, based on a geostatistical method. Second, we analyzed the vehicle mobility by the terramechanical method (i.e., vehicle cone index and Bakker’s theory), and then calculated the mobility cost based on a fuzzy inference method. Finally, based on the calculated mobility cost, the probabilistic roadmap method was used to establish the connected matrix and the multi-dimensional traffic cost evaluation matrix among the sampling nodes, and then an improved A* algorithm was proposed to generate the global route.

Accurately detecting objects in 3D point clouds is critical for achieving precise scene understanding in autonomous driving systems. Cooperative perception, through information exchange among neighboring vehicles, can significantly improve object detection performance even under occlusion. This paper proposes a novel cooperative perception framework based on multi-teacher knowledge distillation for 3D object detection, namely MKD-Cooper. First, we design a Collaborative Attention Fusion (CAF) module that dynamically captures inter-vehicle interactions through channel and spatial attention. By incorporating the CAF module into the CAF network, we effectively aggregate shared deep learning-based features from neighboring vehicles, resulting in a fused feature map that contains rich contextual information. Second, we propose an adaptive multi-teacher knowledge distillation method that adaptively assigns weights to different teacher models based on their current performance, effectively transferring valuable knowledge from multiple excellent teacher models to the student model. Experimental results on the OPV2V and V2XSim 2.0 datasets demonstrate that our method achieves state-of-the-art performance in detection accuracy while exhibiting excellent comprehensive performance between detection accuracy and efficiency. Moreover, field experiments in real urban environments further validate the effectiveness of our approach.

State estimation and mapping are vital prerequisites for autonomous vehicle intelligent navigation. However, maintaining high accuracy in urban environments remains challenging, especially when the satellite signal is unavailable. This paper proposes a novel framework, InLIOM, which tightly couples LiDAR intensity measurements into the system to improve mapping performance in various challenging environments. The proposed framework introduces a stable intensity LiDAR odometry based on scan-to-scan optimization. By extracting features pairwise from intensity information of consecutive frames, this method tackles the instability issue of LiDAR intensity. To ensure the odometry’s robustness, a training-free residual-based dynamic objects filter module is further integrated into the scan-to-scan registration process. The obtained intensity LiDAR odometry solution is incorporated into the factor graph with other multi-sensors relative and absolute measurements, obtaining global optimization estimation. Experiments in indoor and outdoor urban environments show that the proposed framework achieves superior accuracy to state-of-the-art methods. Our approach can robustly adapt to high-dynamic roads, tunnels, underground parking, and large-scale urban scenarios.

Ensuring safety and efficiency in the rapidly advancing autonomous vehicle (AV) industry presents a significant engineering challenge. Comprehensive performance evaluations and critical scenario testing are essential for identifying situations that AVs cannot handle. Thus, generating critical scenarios is a key problem in AV testing system design. This paper proposes a game-theoretic adversarial interaction method to efficiently generate critical scenarios that challenge AV systems. Initial motion prediction for adversarial and surrounding vehicles is based on kinematic models and road constraints, establishing interaction action spaces to determine possible driving domains. A novel evaluation approach combines reachability sets with adversarial intensity to assess collision risks and adversarial strength for any state, used to solve behavior values for each interaction action state. Further, equilibrium action strategies for the vehicles are derived using Stackelberg game theory, yielding optimal actions considering adversarial interactions in the current traffic environment. Simulation results show that the adversarial scenarios generated by this method significantly increase incident rates by 158% to 1313% compared to natural driving scenarios, while ride comfort and driving efficiency decrease, and risk significantly increases. These findings provide critical insights for model improvement and demonstrate the proposed method’s suitability for assessing AV performance in dynamic traffic environments.

Three-dimensional (3D) object detection is crucial for autonomous driving, yet current PointPillar feature-based methods face challenges like under-segmentation, overlapping, and false detection, particularly in occluded scenarios. This paper presents a novel dual-stage improved PointPillar feature-based 3D object detection method (S2*-ODM) specifically designed to address these issues. The first innovation is the introduction of a dual-stage pillar feature encoding (S2-PFE) module, which effectively integrates both inter-pillar and intra-pillar relational features. This enhancement significantly improves the recognition of local structures and global distributions, enabling better differentiation of objects in occluded or overlapping environments. As a result, it reduces problems such as under-segmentation and false positives. The second key improvement is the incorporation of an attention mechanism within the backbone network, which refines feature extraction by emphasizing critical features in pseudo-images and suppressing irrelevant ones. This mechanism strengthens the network’s ability to focus on essential object details. Experimental results on the KITTI dataset show that the proposed method outperforms the baseline, achieving notable improvements in detection accuracy, with average precision for 3D detection of cars, pedestrians, and cyclists increasing by 1.04%, 2.17%, and 3.72%, respectively. These innovations make S2*-ODM a significant advancement in enhancing the accuracy and reliability of 3D object detection for autonomous driving.

Predicting the future trajectories of target agents is critical for the safe operation of autonomous vehicles in complex environments. Accurate trajectory prediction requires the extraction of both temporal and spatial information. To address the limitations of existing static attention methods, which are constrained by fixed historical ranges and spatial radii under limited computational resources, a novel trajectory prediction approach using dynamic spatio-temporal attention is proposed. DSTNet incorporates a multi-scale spatial sparse attention module and a multi-scale historical causal attention module, both aimed at dynamically encoding the spatio-temporal dependencies of the data. These modules are unified with multi-modal interactive attention in a three-attention spatio-temporal module. Additionally, DSTNet includes an anchor-based trajectory refinement module, which adaptively optimizes the coarse-grained trajectories generated by the backbone network. Compared with state-of-the-art methods, DSTNet demonstrates outstanding performance on the Argoverse 1 and Argoverse 2 motion prediction benchmarks, delivering accurate and stable future trajectories. Notably, the model has been successfully deployed on an autonomous vehicle.