Semantic-Aware Autonomy Research Intern

Honda Research Institute USA; Mountain View (CA); On-site; USD 34,000 - 52,000; Full time

Job summary

Honda Research Institute USA in Mountain View invites a research intern to advance semantic-aware interaction and behavior planning for autonomous driving. You will explore scene context and agent intent to inform high-level decisions and integrate with the real-time navigation stack.

The role emphasizes independent research, collaboration with HRI researchers, and evaluating methods in simulation and real-world datasets, with opportunity to contribute to publications and demonstrations.

Qualifications

• Ph.D. candidate in Robotics, CS, EE, or ME.
• Strong background in behavior planning and motion planning.
• Experience in robotics or autonomous systems algorithms.
• Proficient in Python and/or C++.
• Familiar with ML frameworks PyTorch or TensorFlow.
• Ability to conduct independent research.

Responsibilities

• Conduct research on semantic-aware behavior planning and interaction-aware decision making for autonomous driving.
• Develop methods using scene context, agent intent, and semantic relationships.
• Investigate representations like semantic features and interaction graphs.
• Develop decision-making strategies for interactions such as yielding and rerouting.
• Integrate methods with existing navigation and motion-planning algorithms.
• Train and evaluate methods using simulation and real-world datasets.
• Evaluate algorithm-level performance and impact on closed-loop behavior.
• Collaborate with researchers and contribute to publications and demonstrations.

Skills

Behavior planning

Motion planning

Decision making

Autonomous driving

Reinforcement learning

Multi-agent systems

Python

C++

Education

Ph.D. candidate in Robotics/CS/EE/ME

Tools

PyTorch

TensorFlow

ROS/ROS2

Job description

Honda Research Institute USA in Mountain View invites a research intern to advance semantic-aware interaction and behavior planning for autonomous driving. You will explore scene context and agent intent to inform high-level decisions and integrate with the real-time navigation stack.

The role emphasizes independent research, collaboration with HRI researchers, and evaluating methods in simulation and real-world datasets, with opportunity to contribute to publications and demonstrations.