Learning Enhanced Mobility Pipeline

Learning Enhanced Mobility Pipeline - Honda Research Institute USA

Honda Research Institute USA (HRI-US) is seeking a talented and motivated PhD-level research to explore the integration of data-driven learning methods, such as deep reinforcement learning (DRL), with formal control techniques for advanced motion planning and decision-making. The will contribute to the development of hybrid learning-control frameworks for automated driving systems and micromobility platforms operating in complex real-world environments. This is ideal for PhD students with a strong publication record in deep learning and planning who are looking to apply their research to practical robotics and autonomous systems.

Location: Mountain View, CA

Key Responsibilities

Investigate hybrid approaches combining learning-based and control-theoretic methods for motion planning and control.

Design and implement algorithms using DRL, imitation learning, and/or trajectory optimization techniques.

Conduct experiments using simulation environments or real-world robotic platforms.

Analyze and benchmark performance, safety, and generalization of proposed methods.

Collaborate with research mentors and team members to prepare a publishable research outcome.

Present findings to internal teams and publish a paper in top-tier journals or conferences.

Minimum Qualifications

Currently enrolled in a PhD program in Robotics, Computer Science, Electrical Engineering, or a related field.

First-author publications in leading conferences or journals related to deep learning, motion planning, or robotics.

Solid understanding of reinforcement learning, optimal control, and motion planning.

Proficiency in Python and deep learning frameworks such as PyTorch or TensorFlow.

Experience working with simulation tools or real-world robotics environments.

Bonus Qualifications

Research experience in autonomous driving, micromobility, or related domains.

Familiarity with simulation environments such as CARLA, Metadrive, NVIDIA Isaac, AirSim, or similar platforms.

Experience working with datasets relevant to motion planning and autonomous driving, including the Waymo Open Dataset, nuScenes, Argoverse, or KITTI.

Experience combining data-driven and model-based control strategies.

Proficiency in C++ and/or ROS for real-time system development.

Knowledge of uncertainty modeling, risk-aware planning, or interpretability in RL/control.

Years of Work Experience Required:

0

Desired Start Date:

9/15/2025

Duration:

3 Months

Position Keywords:

Offline RL, E2E System

How to apply

Candidates must have the legal right to work in the U.S.A. Please include your Cover Letter and CV in the same document.

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 inquire about your application status.

#J-18808-Ljbffr