Establishing an accurate and computationally efficient model for driving risk assessment, considering the influence of vehicle motion state and kinematic characteristics on path planning, is crucial for generating safe, comfortable, and easily trackable obstacle avoidance paths. To address this topic, this paper proposes a novel dual-layered dynamic path-planning method for obstacle avoidance based on the driving safety field (DSF). The contributions of the proposed approach lie in its ability to address the challenges of accurately modeling driving risk, efficient path smoothing and adaptability to vehicle kinematic characteristics, and providing collision-free, curvature-continuous, and adaptable obstacle avoidance paths. In the upper layer, a comprehensive driving safety field is constructed, composed of a potential field generated by static obstacles, a kinetic field generated by dynamic obstacles, a potential field generated by lane boundaries, and a driving field generated by the target position. By analyzing the virtual field forces exerted on the ego vehicle within the comprehensive driving safety field, the resultant force direction is utilized as guidance for the vehicle’s forward motion. This generates an initial obstacle avoidance path that satisfies the vehicle’s kinematic and dynamic constraints. In the lower layer, the problem of path smoothing is transformed into a standard quadratic programming (QP) form. By optimizing discrete waypoints and fitting polynomial curves, a curvature-continuous and smooth path is obtained. Simulation results demonstrate that our proposed path-planning algorithm outperforms the method based on the improved artificial potential field (APF). It not only generates collision-free and curvature-continuous paths but also significantly reduces parameters such as path curvature (reduced by 62.29% to 87.32%), curvature variation rate, and heading angle (reduced by 34.11% to 72.06%). Furthermore, our algorithm dynamically adjusts the starting position of the obstacle avoidance maneuver based on the vehicle’s motion state. As the relative velocity between the ego vehicle and the obstacle vehicle increases, the starting position of the obstacle avoidance path is adjusted accordingly, enabling the proactive avoidance of stationary or moving single and multiple obstacles. The proposed method satisfies the requirements of obstacle avoidance safety, comfort, and stability for intelligent vehicles in complex environments.

This paper presents a hierarchical lane-changing trajectory planner based on the least action principle for autonomous driving. Our approach aims to achieve reliable real-time avoidance of static and moving obstacles in multi-vehicle interaction scenarios on structured urban roads. Unlike previous studies that rely on subjective weight allocation and single weighting methods, we propose a novel trajectory planning strategy that decomposes the process into two stages: candidate trajectory generation and optimal trajectory decision-making. The candidate trajectory generation employs a path-velocity decomposition method, using B-spline curves to generate a multi-objective optimal lane-changing candidate path. Collision checking eliminates paths at risk of collision with static obstacles. Dynamic programming (DP) and quadratic programming (QP) are then used to plan the velocity of safe paths, generating candidate lane-changing trajectories based on curvature checking. The optimal trajectory decision-making process follows the decision mechanism of excellent drivers. We introduce a comprehensive evaluation function, the average action, which considers safety, comfort, and efficiency based on the least action principle. Feasible trajectories are ranked based on their average action, and the trajectory with the minimum average action and no collision risk with moving obstacles is selected as the tracking target. The effectiveness of the proposed method is validated through two common lane-changing scenarios. The results demonstrate that our approach enables smooth, efficient, and safe lane-changing while effectively tracking the planned velocity and path. This method offers a solution to local trajectory planning problems in complex environments and holds promising prospects in the field of autonomous driving.

Interactive trajectory prediction plays an indispensable role in autonomous driving systems, acting as a key link between perception and decision-making. In complex urban environments, the dynamic interactions among heterogeneous traffic participants and intricate road geometries present significant challenges for accurate trajectory forecasting. To address these challenges, we propose ACDD, a learning-based multi-traffic participant interactive trajectory prediction model equipped with a dual-layer decoder framework. First, we introduce a traffic participant-centered scene modeling method that designs a weighted cost function considering the distance, heading angle, and velocity between different traffic participants to extract the surrounding traffic participants of interest for each traffic participant at the current frame. Based on the extracted neighbors and comprehensive kinematic features, an interaction mask-based mask matrix is computed to facilitate efficient interaction modeling. Based on this mask, we design a spatio-temporal interaction encoder that selectively models interactions only with relevant neighboring traffic participants, significantly reducing computational complexity. Furthermore, we employ a dual-layer decoder architecture guided by intent query vectors to perform secondary optimization of predicted trajectories, effectively mitigating the common issue of mode collapse in traditional single-shot generation methods. Extensive experiments on the Argoverse 2 dataset show that our model achieves competitive performance. Additional ablation studies further validate the effectiveness and rationality of each component within the proposed framework.

To address the issues of low efficiency and non-smooth paths of the A* algorithm in large-scale environments, a terrain-adaptive global path planning method based on Bidirectional Variable Neighborhood Search A* (Terrain-Adaptive Bidirectional Variable Neighborhood Search A*, TA-BVNS-A*) is proposed. Based on the Digital Elevation Model (DEM), the slope resistance and obstacle repulsive potential field are calculated to guide the path to circumvent high-risk areas. Bidirectional alternating search, exponential weighting, and variable neighborhood mechanisms are introduced into the heuristic search to prevent blind expansion. Furthermore, a “node filtering + Bezier smoothing constraint” strategy is employed for post-processing optimization. Multi-scale terrain simulations demonstrate that, after smoothing, the maximum front-wheel steering angle is reduced by over 60% on average, specifically reaching 65.16% in the 100 m × 100 m large-scale map, satisfying vehicle kinematic constraints. This method significantly reduces the number of search nodes, eliminates jagged polylines and redundant nodes, and outputs an efficient and smooth global path that conforms to kinematic constraints.