Autonomous Vehicle Path Control for Dynamic Collision Avoidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous vehicle control systems lack precise and efficient methods for navigating dynamically changing environments, particularly in situations where external objects pose immediate threats, leading to potential collisions.
Innovation Solution
A method involving independent execution of motion prediction and determination algorithms, using probabilistic and short-term movement parameters, combined with emergency collision avoidance and pathfinding algorithms, to dynamically control the vehicle's movement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single integrated control algorithm is used for autonomous vehicle navigation, then the system structure is simpler, but the response speed to spontaneous events is slower and collision avoidance capability is reduced
Solution Approach 1:
The control system is divided into two independent algorithms: a motion prediction algorithm for long-term probabilistic movement prediction and a motion determination algorithm for short-term deterministic collision avoidance. This segmentation allows each algorithm to specialize in its time scale and function, improving overall response speed without excessive complexity
Solution Approach 2:
The system dynamically switches between probabilistic prediction (long-term) and deterministic determination (short-term) based on time scale and situation urgency. The motion determination algorithm operates independently with higher priority for immediate collision avoidance, creating a dynamic adaptive control structure
2Measurement precision
If probabilistic motion prediction is used for long-term movement forecasting, then future movement paths can be anticipated, but computational effort increases
Solution Approach 1:
The computational task is segmented by time scale: probabilistic prediction handles long-term movements with lower computational frequency, while deterministic determination handles short-term movements with higher frequency. This reduces overall computational burden by matching algorithm complexity to time scale requirements
Solution Approach 2:
The system changes the nature of computation based on time scale: using probabilistic parameters for long-term prediction and deterministic parameters for short-term determination. This parameter switching optimizes computational efficiency by applying the appropriate level of complexity for each temporal domain
3Reliability
If the motion determination algorithm executes at high frequency for rapid response, then collision avoidance improves, but system processing load increases
Solution Approach 1:
The motion determination algorithm executes dynamically at higher frequencies only when short-term collision risks are detected, while the motion prediction algorithm runs at lower frequencies for long-term planning. This dynamic frequency adjustment maintains high reliability for collision avoidance while managing processing load
Solution Approach 2:
The motion determination algorithm operates independently with direct access to sensor data and environmental parameters, making autonomous decisions without requiring constant coordination with the prediction algorithm. This self-service capability reduces inter-algorithm processing overhead and system complexity
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The invention relates to a method for determining a direction of travel and/or a future travel path of an at least semi-autonomous or autonomous movable device (12), more particularly a robot and/or a vehicle, in a dynamically variable environment (28), the method comprising at least the following steps: - capturing and/or determining a plurality of environmental parameters, which can each be assigned to at least one moving external object (22, 24, 26) in the environment (28) surrounding the device (12); - executing at least one movement prediction algorithm (36) in order to determine, in each case, at least one probability-theory movement prediction characteristic for detected external objects (22, 24, 26) in accordance with the captured environmental parameters assigned to individual external objects (22, 24, 26); - executing at least one movement determination algorithm (38) in order to determine, in each case, at least one short-term movement characteristic for detected external objects (22, 24, 26) in accordance with the captured environmental parameters assigned to individual external objects (22, 24, 26); wherein the movement prediction algorithm (36) and the movement determination algorithm (38) are executed at least substantially independently of each other in order to determine a future direction of travel and/or a future travel path of the device (12).