18471690. Goal-based Motion Forecasting simplified abstract (Aurora Operations, Inc.)
Goal-based Motion Forecasting
Organization Name
Inventor(s)
Sanjiban Choudhury of Ithaca NY (US)
Sumit Kumar of Sunnyvale CA (US)
Micol Marchetti-bowick of Pittsburgh PA (US)
Goal-based Motion Forecasting - A simplified explanation of the abstract
This abstract first appeared for US patent application 18471690 titled 'Goal-based Motion Forecasting
The abstract describes a computer-implemented method for predicting the intent of actors within an environment by obtaining state data associated with actors, map data indicating lanes, determining potential goals for each actor, and processing the data with a forecasting model to determine forecasted goals, interactions, and trajectories.
- Method for predicting actor intent within an environment
- Obtaining state data and map data to determine potential goals for actors
- Processing data with a forecasting model to forecast goals, interactions, and trajectories
- Utilizing machine learning to predict actor behavior
- Enhancing understanding of actor intentions and interactions within a given environment
Potential Applications: - Autonomous vehicles - Robotics - Surveillance systems - Gaming industry - Traffic management systems
Problems Solved: - Improving safety in dynamic environments - Enhancing decision-making processes for automated systems - Predicting and preventing potential conflicts between actors
Benefits: - Increased efficiency in automated systems - Enhanced situational awareness - Improved overall performance and safety in various applications
Commercial Applications: Predictive analytics for autonomous vehicles and robotics industries
Prior Art: Researchers may explore similar patents related to machine learning forecasting models for predicting human behavior in dynamic environments.
Frequently Updated Research: Stay informed about advancements in machine learning algorithms for predicting actor intent in various environments.
Questions about the technology: 1. How does this method improve decision-making processes for autonomous systems? 2. What are the potential limitations of using machine learning for predicting actor intent in dynamic environments?
Original Abstract Submitted
Example aspects of the present disclosure relate to an example computer-implemented method for predicting the intent of actors within an environment. The example method includes obtaining state data associated with a plurality of actors within the environment and map data indicating a plurality of lanes of the environment. The method includes determining a plurality of potential goals each actor based on the state data and the map data. The method includes processing the state data, the map data, and the plurality of potential goals with a machine-learned forecasting model to determine (i) a forecasted goal for a respective actor of the plurality of actors, (ii) a forecasted interaction between the respective actor and a different actor of the plurality of actors based on the forecasted goal, and (iii) a continuous trajectory for the respective actor based on the forecasted goal.
