Research Intern: Real-Time End-to-End Autonomous Driving

Honda Research Institute USA; Mountain View (CA); On-site; USD 34,000 - 55,000; Full time

Job summary

Honda Research Institute USA in Mountain View, CA is offering a Research Intern position focused on real-time end-to-end autonomous driving. You will work on training and distilling generative and autoregressive models to enable real-time inference within autonomous driving systems.

The internship involves hands-on research, implementation in PyTorch/TensorFlow, and publication of results at top conferences or journals. Duration: 3 months starting May 2027, based in Mountain View.

Qualifications

• Enrolled in a Ph.D. program in Robotics, Electrical/Computer Engineering, Machine Learning, or a related field.
• Research experience in machine learning, decision-making, motion planning, and robotics.
• Experience with ML frameworks such as PyTorch or TensorFlow.
• Excellent programming skills in Python.

Responsibilities

• Train and distill a generative and an autoregressive model for the end-to-end autonomous driving task.
• Apply model adaptation techniques to achieve real-time inference capability.
• Benchmark the developed algorithm's performance in closed-loop simulations.
• Publish findings in a top-tier conference or journal.

Skills

Python

PyTorch

TensorFlow

ML

Robotics

Education

Ph.D. student

Job description

Research Intern: Real-Time End-to-End Autonomous Driving - Honda Research Institute USA

Research Intern: Real-Time End-to-End Autonomous Driving

Job Number: P26INT-06

Honda Research Institute USA (HRI-US) is seeking a self-motivated research intern to join our CI-Mobility Research team. This individual will contribute to the development of efficient generative and autoregressive models for end-to-end autonomous driving. This work will involve training and/or distilling an efficient generative model in combination with an autoregressive model to address the long-tail nature of the autonomous driving task. A key requirement will be real-time inference, which will require adapting the final model to achieve an efficient architecture.

Mountain View, CA

Key Responsibilities

• Train and distill a generative and an autoregressive model for the end-to-end autonomous driving task.
• Apply model adaptation techniques to achieve real-time inference capability.
• Benchmark the developed algorithm's performance in closed-loop simulations.
• Publish findings in a top-tier conference or journal.

Minimum Qualifications

• Currently enrolled in a Ph.D. program in Robotics, Electrical/Computer Engineering, Machine Learning, or a related field.
• Research experience in machine learning, decision-making, motion planning, and robotics.
• Experience with ML frameworks such as PyTorch or TensorFlow.
• Excellent programming skills in Python.

Bonus Qualifications

• Publication record in the areas of machine learning, decision-making and motion planning at top-tier venues such as NeurIPS, ICLR, CVPR, ICML, AAAI, ICRA, IROS, etc.

Years of Work Experience Required 0

Desired Start Date May 2027

Internship Duration 3 Months

Position Keywords

Generative models, Autoregressive models, Knowledge distillation

For California applicants: Please review the Honda California Job Applicant Privacy Notice before submitting your application.

For California applicants: Please review the Honda California Job Applicant Privacy Notice before submitting your application.