Occlusion and Uncertainty Aware Planning for Navigation - Honda Research Institute USA

Occlusion and Uncertainty Aware Planning for Navigation

Your application is being processed

Occlusion and Uncertainty Aware Planning for Navigation

Job Number: P24INT-39
​This internship focuses on developing robust motion planning algorithms for autonomous driving or general robotic navigation under conditions of partial observability and environmental uncertainty. The intern will explore planning strategies that explicitly account for occluded areas, dynamic objects, and uncertain intentions of other agents in the scene. Emphasis will be placed on integrating safety assurance mechanisms and contingency-aware decision-making into a practical autonomous navigation stack. The intern will collaborate closely with HRI scientists and engineers and have the opportunity to publish their findings at leading academic conferences.
Mountain View, CA

 

Key Responsibilities

 
  • ​Conduct an extensive literature review on occlusion-aware planning, probabilistic risk assessment, and contingency planning under uncertainty.
  • Design, implement, and evaluate motion planning algorithms that reason over occluded spaces using prediction bounds and probabilistic representations.
  • Incorporate safety filters and verification methods to ensure robust behavior under worst-case scenarios.
  • Develop fallback policy-based planning techniques that adapt to dynamically revealed information in real-time.
  • Enhance the existing motion planning stack in simulation environments with uncertainty modeling and partial observability constraints.
  • Collaborate with HRI scientists and engineers to integrate, test, and validate methods on simulated or real-world scenarios.
  • Publish research results in leading academic conferences or journals.

 

Minimum Qualifications

 
  • ​Ph.D candidate in Robotics, Computer Science, Mechanical Engineering, or similar fields.
  • Strong background and experience in at least one of the followings: motion planning under uncertainty, safety-critical control, probabilistic risk modeling, POMDPs, or contingency planning, Interaction aware planning.
  • Must have experience with coding in C++, Python and MATLAB.
  • Experience working with simulation frameworks for autonomous driving.
  • Self-driven and capable of independent research and implementation.

 

Bonus Qualifications

  • Research experience in Robotics/Automated vehicles Motion Planning and Control, Machine learning.
  • Prior published research on occlusion handling, prediction under uncertainty, or robust planning.
  • Knowledge of safety guarantees in motion planning (e.g., Reachability Analysis).
  • Strong software development experience.
  • Experience with using ROS-framework packages.
  • Experience using public datasets and simulators for navigation research.

 

Years of Work Experience Required  0
Desired Start Date 9/15/2025
Internship Duration 3 Months
Position Keywords Occlusion-aware planning, uncertainty-aware decision-making, safety filters, contingency planning, probabilistic motion planning, autonomous vehicles, Interaction-aware decision making.

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.