Multi-mode sensing trajectory planning method and system for new energy vehicle

By using a multimodal perception trajectory planning method, the problems of robustness of sensor data fusion and insufficient energy management in new energy vehicles are solved. It realizes adaptive weight adjustment of sensor data and deep fusion of multimodal information, which improves the safety and energy efficiency of the system and extends the driving range.

CN121375852AInactive Publication Date: 2026-01-23HANGZHOU POLYTECHNIC
0 Cites 0 Cited by

Patent Information

Application Number
CN202511872836.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-12-12
Publication Date
2026-01-23
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Existing autonomous driving trajectory planning technologies in new energy vehicles suffer from problems such as insufficient robustness of multimodal sensor data fusion, inadequate coupling between energy management and trajectory planning, failure to consider the uncertainty of obstacle trajectory prediction, and difficulty in balancing the real-time performance and optimization quality of optimization algorithms, resulting in low system reliability and energy efficiency.

Method used

A multimodal perception trajectory planning method is adopted. Multimodal sensor data is acquired, preprocessed, and features are extracted. A cross-attention fusion network is used to achieve robust fusion and adaptive weight adjustment of sensor data. Combined with dynamic obstacle prediction and safety buffer setting, a behavior decision input state vector is constructed, candidate trajectories are generated and comprehensively evaluated, and finally the optimized trajectory is obtained through nonlinear optimization.

Benefits of technology

It achieves adaptive weight adjustment of sensor data and deep fusion of multimodal information, which improves the accuracy of environmental perception and the safety and reliability of the system, while optimizing energy management, extending driving range and reducing operating costs.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to the technical field of new energy automobile intelligent driving, and discloses a new energy automobile multi-mode sensing trajectory planning method and system, and the method comprises the steps: obtaining multi-mode original sensor data, and carrying out the preprocessing; feature extraction and cross attention fusion are carried out; performing dynamic obstacle prediction, and setting a dynamic safety buffer area; constructing a behavior decision input state vector, and reasoning and adjusting a behavior decision; generating a candidate trajectory curve and performing feasibility check on the candidate trajectory curve; comprehensively evaluating the candidate track set; predicting a nonlinear optimization problem by taking the initial optimal trajectory curve as a reference trajectory, and solving and verifying the nonlinear optimization problem; according to the method, robust fusion and adaptive weight adjustment of multi-modal sensor data are realized by establishing a sensor health monitoring mechanism, a dynamic weight distribution strategy and a cross attention fusion network.
Need to check novelty before this filing date? Find Prior Art