Speed Planning Guidance Line for Natural Deceleration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous driving vehicles struggle to plan and execute natural deceleration, leading to discomfort for passengers as conventional methods separate planning and control, failing to replicate human-like deceleration profiles.
Innovation Solution
A method for planning a deceleration trajectory based on a natural deceleration profile for autonomous driving vehicles, involving determining the current speed, generating a speed guideline, and optimizing a total cost function using Quadratic programming to control the vehicle's speed, thereby mimicking human-like natural deceleration without engaging brakes or accelerators.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If conventional planning and control modules operate separately, then the autonomous vehicle can execute basic deceleration, but the deceleration feels unnatural and uncomfortable for passengers
Solution Approach 1:
The patent merges the planning module and control module into an integrated system that jointly optimizes deceleration trajectories. The controller receives inputs from both modules and executes unified control commands that combine high-level planning intentions with low-level control adjustments, enabling natural deceleration while maintaining modular architecture benefits.
Solution Approach 2:
The system dynamically adjusts deceleration parameters in real-time based on vehicle state, road conditions, and passenger comfort requirements. The controller continuously modifies acceleration commands within the natural deceleration range [-2, 0] m/s², creating adaptive and flexible control that responds to changing conditions rather than following fixed deceleration schedules.
2Reliability
If the autonomous vehicle uses brake engagement for deceleration, then stopping control is precise, but passenger comfort deteriorates due to abrupt deceleration
Solution Approach 1:
The system performs preliminary deceleration using engine braking and aerodynamic drag before final stopping, reserving brake engagement for precise position correction. The controller calculates required deceleration distance in advance and distributes braking effort across multiple phases, applying brakes only when necessary to achieve accurate stopping positions without abrupt passenger-perceivable deceleration.
Solution Approach 2:
The system changes the deceleration parameter range to [-2, 0] m/s² to exclude aggressive braking and achieve natural deceleration. This parameter constraint transforms the control strategy from brake-centric to engine-brake-aerodynamic drag-centric, maintaining stopping precision while improving comfort through softer deceleration profiles.
3Ease of operation
If the autonomous vehicle releases the accelerator for natural deceleration, then passenger comfort improves, but deceleration control precision deteriorates
Solution Approach 1:
The controller implements closed-loop feedback by continuously monitoring vehicle speed, position, and deceleration rate, then adjusting acceleration commands to maintain adherence to the natural deceleration profile. The system compares actual deceleration against the target profile and applies corrective commands within the [-2, 0] m/s² range, ensuring precise control while preserving the natural feel of accelerator release deceleration.
Data Source
AI summary
A method, apparatus, and system for planning a deceleration trajectory based on a natural deceleration profile for an autonomous driving vehicle (ADV) is disclosed. In one embodiment, in response to a request for driving in a natural deceleration mode, a current speed of the ADV is determined. A speed guideline is generated based on a predetermined natural deceleration profile associated with the ADV in view of the current speed of the ADV. A speed planning operation is performed by optimizing a total cost function based on the speed guideline to determine speeds of a plurality of trajectory points along a trajectory planned to drive the ADV. A number of control commands are generated based on the speed planning operation to control the ADV with the planned speeds along the trajectory, such that the ADV naturally slows down according to the predetermined natural deceleration profile.