Dynamic Multi-Segment Path Shaping for ADAS
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current motion path search algorithms for ADAS systems require significant computing resources and are not feasible for low-power embedded applications, and they lack the ability to adjust paths based on external conditions like undrivable road segments, leading to inefficiencies in vehicle automation.
Innovation Solution
An autonomous vehicle control system that uses sensors like cameras and lidar to detect objects and generate dynamic multi-segment paths and speed profiles, avoiding undrivable areas by calculating shaping points and adjusting vehicle trajectories using quintic functions to manage lateral acceleration, thereby reducing computational complexity and ensuring safety and comfort.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If current motion path search algorithms are used to generate vehicle paths, then path planning capability is provided, but computing resource requirements become excessive for low-power embedded applications
Solution Approach 1:
The path planning process is divided into multiple discrete segments or steps. The system segments the path generation into: (1) generating candidate paths, (2) evaluating paths against constraints, (3) selecting optimal path. This segmentation allows the use of simpler, less computationally intensive algorithms at each stage rather than requiring complex exhaustive search algorithms, thereby reducing computing resource requirements while maintaining path planning capability.
Solution Approach 2:
The system performs preliminary actions by pre-defining constraint parameters, undrivable areas, and path evaluation criteria before the actual path planning execution. Map data, road boundaries, and obstacle information are pre-processed and stored as constraint sets. This preliminary preparation reduces the computational burden during real-time path generation by eliminating the need for complex on-the-fly calculations of these fundamental parameters.
2Device complexity
If current ADAS systems generate motion paths without considering external conditions, then path generation is simpler, but the system cannot adjust for undrivable road segments
Solution Approach 1:
The path generation system is made dynamic by allowing real-time adjustment of path parameters based on external conditions. The system dynamically evaluates candidate paths against currently active constraints (such as undrivable areas, weather conditions, traffic conditions) and adjusts the selected path parameters accordingly. This dynamic adaptation enables the system to respond to changing external conditions without requiring complete re-planning, balancing simplicity with adaptability.
Solution Approach 2:
The system changes path parameters (such as lateral offset, curvature, speed profile) based on external conditions like undrivable road segments. When undrivable areas are detected, the system modifies path parameters to route around these areas while maintaining drivability constraints. This parameter adjustment mechanism allows the system to adapt to external conditions through relatively simple modifications to existing path parameters rather than complete path regeneration.
Data Source
AI summary
The present application relates to determining a location of an object in response to a sensor output, generating a first vehicle path in response to the location of the object and a map data, determining an undrivable area within the first vehicle path, generating a waypoint outside of the undrivable area, generating a second vehicle path from a first point on the first vehicle path to the waypoint and a third vehicle path from the waypoint to a second point on the first vehicle path such that the second vehicle path and the third vehicle path are outside of the undrivable area, generating a control signal in response to the second vehicle path, the third vehicle path and and controlling a vehicle in response to the control signal such that the vehicle follows the second vehicle path and the third vehicle path.