17938146. TRAJECTORY PLANNING SYSTEM FOR AN AUTONOMOUS VEHICLE WITH A REAL-TIME FUNCTION APPROXIMATOR simplified abstract (GM Global Technology Operations LLC)

TRAJECTORY PLANNING SYSTEM FOR AN AUTONOMOUS VEHICLE WITH A REAL-TIME FUNCTION APPROXIMATOR

Organization Name

GM Global Technology Operations LLC

Inventor(s)

Daniel Aguilar Marsillach of Detroit MI (US)

Upali P. Mudalige of Rochester Hills MI (US)

TRAJECTORY PLANNING SYSTEM FOR AN AUTONOMOUS VEHICLE WITH A REAL-TIME FUNCTION APPROXIMATOR - A simplified explanation of the abstract

This abstract first appeared for US patent application 17938146 titled 'TRAJECTORY PLANNING SYSTEM FOR AN AUTONOMOUS VEHICLE WITH A REAL-TIME FUNCTION APPROXIMATOR

Simplified Explanation

The patent application describes a trajectory planning system for autonomous vehicles that uses controllers to avoid obstacles and select safe paths.

Key Features and Innovation

• Controllers communicate with external vehicle networks to gather data on moving obstacles.
• Real-time ego states of the vehicle are approximated using a function approximator trained through supervised learning.
• Multiple relative state trajectories are computed to avoid collisions.
• The system selects the safest trajectory for the vehicle to follow during maneuvers.

Potential Applications

This technology can be applied in:

• Autonomous vehicles for safer navigation.
• Robotics for obstacle avoidance.
• Drones for efficient path planning.

Problems Solved

• Avoiding collisions with moving obstacles.
• Improving the safety and efficiency of autonomous vehicles.
• Enhancing maneuverability in complex environments.

Benefits

• Increased safety for autonomous vehicles.
• Improved navigation in dynamic environments.
• Enhanced decision-making capabilities for vehicles.

Commercial Applications

Trajectory Planning System for Autonomous Vehicles: Enhancing Safety and Efficiency

This technology can revolutionize the autonomous vehicle industry by providing advanced trajectory planning systems that ensure safe and efficient navigation in complex environments. Companies developing autonomous vehicles can integrate this system to enhance the performance and reliability of their products, leading to increased market competitiveness and customer trust.

Prior Art

No prior art information is available at this time.

Frequently Updated Research

There is ongoing research in the field of autonomous vehicle trajectory planning, focusing on improving real-time decision-making algorithms and enhancing obstacle avoidance strategies.

Questions about Trajectory Planning System for Autonomous Vehicles

Question 1

How does the function approximator in the system help in approximating real-time ego states?

The function approximator in the system uses supervised learning to train on offline ego states, allowing it to estimate real-time ego states accurately.

Question 2

What are the potential commercial implications of integrating this trajectory planning system into autonomous vehicles?

Integrating this system can lead to safer autonomous vehicles, increased market competitiveness, and enhanced customer trust, ultimately driving the growth of the autonomous vehicle industry.

Original Abstract Submitted

A trajectory planning system for an autonomous vehicle includes one or more controllers in electronic communication with one or more external vehicle networks that collect data with respect to one or more moving obstacles located in an environment surrounding the autonomous vehicle. The one or more controllers approximate a set of real-time ego states of the autonomous vehicle by a function approximator, where the function approximator has been trained during a supervised learning process with the set of offline ego states as a ground-truth dataset. The one or more controllers compute a plurality of relative state trajectories for the autonomous vehicle, where the plurality of relative state trajectories avoid intersecting the set of real-time ego states of autonomous vehicle. The one or more controllers select a trajectory from the plurality of relative state trajectories for the autonomous vehicle, where the autonomous vehicle follows the trajectory while performing the maneuver.