Autonomous Vehicle Speed Planning Tapered Transitions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional motion planning for autonomous driving vehicles does not accurately account for differences in vehicle types, leading to potentially rough or unsafe speed transitions when encountering changes in speed limits, such as sudden drops from high to low speed limits, often resulting in abrupt brake controls.
Innovation Solution
A speed planning system that generates tapered speed limits based on cost functions, allowing for gradual speed reductions from one speed limit to another, which are used to create trajectory candidates for controlling the vehicle, thereby minimizing abrupt brake applications.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If conventional motion planning applies same speed control to all vehicle types, then device complexity is reduced, but manufacturing precision and operational accuracy deteriorate due to inability to account for vehicle-specific characteristics
Solution Approach 1:
The patent applies local quality by introducing vehicle-type-specific parameters and cost functions tailored to different vehicle characteristics (e.g., acceleration capabilities, braking distances, vehicle mass). Each vehicle type receives customized motion planning parameters rather than uniform control, improving speed transition accuracy while maintaining manageable system complexity through modular parameter adjustment.
2Productivity
If conventional motion planning uses abrupt speed limit changes, then productivity is improved by reducing planning time, but object-generated harmful factors increase due to abrupt braking and rough transitions
Solution Approach 1:
The patent applies preliminary action by pre-calculating optimal speed profiles and trajectory candidates that incorporate gradual speed transitions. The system prepares multiple pre-planned trajectory options with smooth acceleration and deceleration curves before execution, allowing the planner to select the most appropriate path without requiring real-time abrupt adjustments, thus maintaining efficiency while eliminating harmful abrupt braking.
Solution Approach 2:
The patent applies dynamics by implementing dynamic speed adjustment through cost functions that evaluate multiple trajectory candidates with varying speed profiles. The system dynamically selects and adjusts trajectories based on real-time conditions, vehicle type, and speed limit changes, enabling smooth and adaptive speed transitions rather than fixed abrupt changes, thereby reducing harmful braking while maintaining planning efficiency.
3Device complexity
If conventional motion planning estimates difficulty only from curvature and speed, then device complexity is reduced, but measurement precision deteriorates by failing to consider vehicle type differences
Solution Approach 1:
The patent applies parameter changes by extending the path difficulty estimation to include vehicle-type-specific parameters such as acceleration capabilities, braking distances, maximum speeds, and vehicle mass. The cost functions incorporate these additional parameters to accurately evaluate trajectory difficulty for different vehicle types, improving measurement precision while maintaining reasonable system complexity through structured parameter integration.
Data Source
AI summary
In one embodiment, a speed planning system receives speed limit information for an autonomous driving vehicle (ADV), where the speed limit information includes a change in road speed limit for a current road of the ADV. The system determines a tapered speed limit corresponding to the current road based on the speed limit information, where the tapered speed limit correspond to a gradual speed reduction from a first road speed limit to a second road speed limit. The system determines a cost function based on the tapered speed limit and the first and second road speed limits. The system generates a number of trajectory candidates based on the cost function. The system selects a trajectory based on the trajectory candidates to control the ADV using the selected trajectory.