Your application is being processed
Postdoctoral Scientist in Visuotactile Perception and Planning for Object Manipulation
Job Number: P22T07
Honda Research Institute USA (HRI-US) in San Jose, California, is seeking a highly motivated postdoctoral scientist at the intersection of planning and perception, combining computer vision and tactile sensing (visuotactile), for object manipulation with a multi-fingered hand. The focus of the research is to develop perception algorithms to estimate object states such as object 6D pose and finger-object contact states like slip, and to integrate these algorithms with a planner to perform manipulation tasks such as in-hand repositioning of objects. The successful candidate will develop perception algorithms in simulation, integrate them with a planner, deploy them on state-of-the-art robotic platforms with multi-fingered hands, and ensure that their performance on the robot matches that of the simulations. The ideal candidate will have experience with deep learning platforms, programming, and ROS, as well as training multisensory machine learning algorithms for robotic manipulation and planning.
San Jose, CA
|
|
| Desired Start Date |
4/1/2024 |
| Duration |
3 Year |
| Position Introduction |
Honda Research Institute USA (HRI-US) in San Jose, California, is seeking a highly motivated postdoctoral scientist at the intersection of planning and perception, combining computer vision and tactile sensing (visuotactile), for object manipulation with a multi-fingered hand. The focus of the research is to develop perception algorithms to estimate object states such as object 6D pose and finger-object contact states like slip, and to integrate these algorithms with a planner to perform manipulation tasks such as in-hand repositioning of objects. The successful candidate will develop perception algorithms in simulation, integrate them with a planner, deploy them on state-of-the-art robotic platforms with multi-fingered hands, and ensure that their performance on the robot matches that of the simulations. The ideal candidate will have experience with deep learning platforms, programming, and ROS, as well as training multisensory machine learning algorithms for robotic manipulation and planning. |
| Key Responsibilities |
- Develop algorithms for multi-modal (vision and tactile) perception and integrate it with planning and control modules for object manipulation using a multi-fingered hand
- Deploy algorithms on a robotic platform and demonstrate their application on a set of tasks (e.g. in-hand repositioning of objects)
- Collaborate with local and international stakeholders to integrate planning, control, and perception for object manipulation
- Publish research results at top-tier conferences and journals in robotics and machine learning
|
| Minimum Qualifications |
- Ph.D. in computer science, robotics, or a related field
- Experience with deep learning and deep learning platforms such as PyTorch
- Strong programming skills in Python or C++
- Familiarity with ROS and developing end-to-end systems
- Experience training and testing machine learning algorithms and deploying models on a robotic platform
|
|
|
|
Please include a cover letter detailing your relevant experiences. We value diverse experiences and skills and are interested in your unique perspective.
Please also include in application if you currently require Visa sponsorship for employment status? (Such as, H1B, TN, O1)
|
2-5
|
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.
