Autonomous Vehicle Trajectory Planning for Predicted Obstacle Paths
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in safely traversing transportation networks due to the inability to accurately detect and predict static and dynamic objects, leading to inefficiencies and potential collisions.
Innovation Solution
A method and system for object avoidance in autonomous vehicles that utilize sensors and trajectory planning algorithms to detect static and dynamic objects, predict their trajectories, and generate smooth, safe paths by integrating HD map data and teleoperation inputs, allowing for remote operation and adjustment of speed and trajectory in real-time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If autonomous vehicles rely solely on automated detection and trajectory prediction algorithms, then operational efficiency is improved, but safety and reliability deteriorate due to inability to accurately detect and predict static and dynamic objects
Solution Approach 1:
The patent introduces a teleoperation system as an intermediary between the autonomous vehicle's automated systems and human operators. When the trajectory planning system identifies uncertain situations or potential collisions, it automatically requests teleoperation assistance. A remote operator then provides corrective steering inputs or trajectory adjustments, serving as a mediator that enhances safety without compromising the autonomous vehicle's operational efficiency in normal conditions.
2Measurement precision
If the vehicle system integrates multiple data sources including HD map data and teleoperation inputs, then measurement precision and detection accuracy are improved, but device complexity increases
Solution Approach 1:
The patent segments the trajectory planning system into distinct functional modules: an automated trajectory planning module that processes sensor data and HD map information, a teleoperation module that receives and processes remote operator inputs, and an integration module that combines these data streams. This segmentation allows each module to specialize in specific data processing tasks, improving overall detection accuracy while managing system complexity through modular architecture.
Solution Approach 2:
The trajectory planning system is designed with multi-functionality to handle diverse data sources uniformly. It processes sensor data from the autonomous vehicle's own sensors, HD map data from external sources, and teleoperation inputs from remote operators through a common processing framework. This universal approach allows the system to integrate multiple data sources effectively, improving measurement precision without proportionally increasing complexity.
3Reliability
If the trajectory planning algorithm generates smooth and safe paths by integrating multiple data sources, then navigation reliability is improved, but computational time and processing complexity increase
Solution Approach 1:
The system performs preliminary processing of HD map data and sensor information to pre-calculate potential trajectory options and identify hazardous areas in advance. By preparing this information beforehand, the trajectory planning algorithm can quickly generate safe paths when needed, improving navigation reliability without excessive computational delay during critical decision-making moments.
Solution Approach 2:
The trajectory planning system implements a hierarchical approach where it first generates a subset of plausible trajectories based on prioritized data sources (own sensors and HD maps), then selectively refines these options using additional teleoperation inputs only when necessary. This partial action approach ensures navigation reliability for common scenarios while reducing computational time by avoiding full processing for every possible trajectory option.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Object avoidance by an autonomous vehicle (AV) is disclosed. A method includes detecting a first object along a coarse driveline of a drivable area of the AV; receiving a predicted path of the first object; determining, based on the predicted path of the first object, an adjusted drivable area; and determining a trajectory of the AV through the adjusted drivable area. A system includes a trajectory planner configured to detect a first object along a coarse driveline of a drivable area of the AV; receive a predicted path of the first object; determine, based on the predicted path of the first object, an adjusted drivable area; and determine a trajectory of the AV through the adjusted drivable area.