Job Number: P24F06
Honda Research Institute USA (HRI-US) in San Jose, California, is looking for a passionate and self-motivated research scientist to join our Robotics Division. Through the creation of avatars and autonomous intelligent entities, Honda’s robotics program is positioning robots to work alongside humans in collaborative, scalable networks aimed at extending human capabilities. Research scientist specializing in Robot Manipulation Learning will innovate and participate in key areas of robotic intelligence development that will enable robots to perceive, understand, perform complex dexterous manipulations in the real world and adapt.
San Jose, CA

MINIMUM QUALIFICATIONS

• Ph.D. in robotics, mechanical engineering, electrical engineering, computer science, or a related field.
• Expert Knowledge on learning-based methods such as reinforcement learning, generative models and inference.
• Experience with robotic manipulation, planning, control, and dynamics for autonomous systems.
• Familiarity with transformer models and (multimodal) foundation models (e.g. VLMs).
• Solid knowledge of fundamentals of robotics. (e.g. robot kinematics and dynamics, control systems, haptics.)
• Strong track record of publishing in top robotics and machine learning venues.
• Solid programming skills in C++ or Python and strong familiarity with ROS.
• Self-motivated to advance the project and deliver on time.
• Strong written and oral communication skills including development and delivery of presentations, papers, and technical documents.

BONUS QUALIFICATIONS

• Hands-on experience on development and successful implementation of planning, control and recovery algorithms for real-world contact-rich manipulation tasks.
• Experience with policy deployment on multi-fingered robots.
• Experience in building and implementing multimodal vision language action models (MMVLA) for manipulation tasks.

YEARS OF WORK EXPERIENCE REQUIRED

5 years

• Research, ideate, and implement robot cognition and reasoning algorithms for adaptive intelligence to enable learning robust behaviors and recover from failures.
• Research & Development of machine learning algorithms for telemanipulation, contact rich dexterous manipulation, and object pose estimation.
• Implementing the algorithms in simulation and verify on multi-fingered robot hardware.
• Validate the results through comprehensive data analysis and successful demonstrations on hardware.
• Deliver results in accordance with the project timelines.
• Assist with compiling written and oral reports for executives within the company and performing demos.
• Contribute to the portfolio of patents, academic publications, and prototypes to demonstrate research value.
• Collaborate with our teams of scientists and engineers in Honda’s regional and global R&D offices, as well as with our partners in academia and industry.