17933587. SYSTEM AND METHOD FOR EFFICIENT PLANNING UNDER UNCERTAINTY FOR AUTONOMOUS VEHICLES simplified abstract (GM GLOBAL TECHNOLOGY OPERATIONS LLC)

SYSTEM AND METHOD FOR EFFICIENT PLANNING UNDER UNCERTAINTY FOR AUTONOMOUS VEHICLES

Organization Name

GM GLOBAL TECHNOLOGY OPERATIONS LLC

Inventor(s)

Sayyed Rouhollah Jafari Tafti of Troy MI (US)

Brent Navin Roger Bacchus of Sterling Heights MI (US)

SYSTEM AND METHOD FOR EFFICIENT PLANNING UNDER UNCERTAINTY FOR AUTONOMOUS VEHICLES - A simplified explanation of the abstract

This abstract first appeared for US patent application 17933587 titled 'SYSTEM AND METHOD FOR EFFICIENT PLANNING UNDER UNCERTAINTY FOR AUTONOMOUS VEHICLES

Simplified Explanation

The method described in the patent application involves efficient autonomous driving planning by analyzing current and predicted driving scene data to determine the best trajectory planning process for a host vehicle. Here are the key points of the innovation:

• Receiving current driving-scene data and predicted driving-scene data
• Converting data into first and second scene-graphs
• Determining scene change metrics using the scene-graphs
• Selecting trajectory planning process based on scene change metrics

---

1. 1. 1. Potential Applications of this Technology

- Autonomous vehicles - Traffic management systems - Fleet management solutions

1. 1. 1. Problems Solved by this Technology

- Improving safety in autonomous driving - Enhancing efficiency in route planning - Optimizing traffic flow

1. 1. 1. Benefits of this Technology

- Reduced accidents and collisions - Increased traffic efficiency - Enhanced overall driving experience

1. 1. 1. Potential Commercial Applications of this Technology
         1. Optimizing Autonomous Driving Planning for Efficiency

1. 1. 1. Possible Prior Art

There are existing methods for autonomous driving planning that focus on real-time data analysis and trajectory optimization. However, the specific approach outlined in this patent application, which involves comparing current and predicted driving scenes to determine the best trajectory planning process, appears to be a novel innovation in the field.

---

1. 1. 1. Unanswered Questions

1. 1. 1. 1. How does the method handle sudden changes in the driving scene data?

The patent application does not provide details on how the method adapts to unexpected changes in the driving scene data, such as sudden obstacles or road conditions. Further information on the real-time decision-making process would be beneficial.

1. 1. 1. 1. What are the limitations of the scene change metrics in selecting the trajectory planning process?

While the patent application mentions using scene change metrics to choose between trajectory planning processes, it does not elaborate on the potential drawbacks or limitations of this approach. Understanding the factors that may impact the accuracy of the scene change metrics would provide valuable insights into the method's effectiveness.

Original Abstract Submitted

A method for efficient autonomous driving planning includes receiving a current driving-scene data and a predicted driving-scene data. The current driving-scene data is indicative of a current driving scene around a host vehicle. The predicted driving-scene data is indicative of a predicted driving scene around the host vehicle. The predicted driving scene around the host vehicle is different from the current driving scene around the host vehicle. The method further includes converting the current driving-scene data and the predicted driving-scene data into a first scene-graph and a second scene-graph, respectively. The method further includes determining a plurality of scene change metrics using the first scene-graph and the second scene-graph. The method further includes selecting between a first trajectory planning process and a second trajectory planning process based on the plurality of scene change metrics.