Behavior Modeling and Interactive Prediction - Honda Research Institute USA

Behavior Modeling and Interactive Prediction

Your application is being processed

Behavior Modeling and Interactive Prediction

Job Number: P23INT-39
​This project focuses on computational modeling and prediction for human drivers. The task will incorporate predicting the behavior of traffic agents, including in dynamic scenes where the agent may interact with or respond to their surroundings. The project involves design and development of interactive probabilistic models and optimization of the agent behavior using technologies such as deep learning, model predictive control, behavior cloning, and/or reinforcement learning.
San Jose, CA

 

Key Responsibilities

  • Modeling Behavior Dynamics for predicting social agents
  • Build a behavior modeling framework to understand and predict interactions between autonomous agents
  • Implement the algorithm and analyze it's performance and safety

 

 

Minimum Qualifications

  • M.S. candidate in robotics, computer science, electrical engineering, or related field
  • Research experience in planning, machine learning, or robotics
  • Excellent programming skills in C++ and Python

 

 

Bonus Qualifications

  • Ph.D. candidate in robotics, computer science, electrical engineering, or related field
  • Experience with ROS (Robot Operating System)
  • Publication record of planning or prediction on robotic systems
  • Experience with Waymo Open Motion Dataset, or UniTraj

 

Desired Start Date 01/06/2025 

 

Duration

 

3 Months

 

Alternate Way to Apply

Send an e-mail to careers@honda-ri.com with the following:
- Subject line including the job number(s) you are applying for 
- Recent CV 
- A cover letter highlighting relevant background (Optional)

Please, do not contact our office to inquiry about your application status.