Intern, Research, Robot Learning

Key Skills

C Programming, C++, Cloud computing, Data science techniques, Java Programming, Machine learning techniques, MATLAB Programming, Python Programming, PyTorch, R Programming, Scala Programming, SQL, TensorFlow

Job Description

As a 2023 Robot Learning Intern at the Autodesk Robotics Lab, you'll conduct cutting-edge research and build advanced robotics software and capabilities. We are a team of researchers, engineers, and industry domain experts working on projects that range from reinforcement learning, deep learning, computer vision, motion planning, simulation, human-robot cooperation and more for robotic applications in manufacturing and construction.

We are looking for interns interested in any of the following topics:

• learning for contact-rich manipulation
• learning multimodal policies from vision, tactile, and F/T
• generalized grasp pose estimation via tactile sensing
• closing the sim2real gap for contact-rich manipulation

We have state-of-the-art robots, computing and sensing capabilities in-house for conducting advanced research and building full system demonstrations at Pier 9 in San Francisco, with a beautiful view of the San Francisco Bay. 

Autodesk's Robotics Lab is active in the wider research community, targeting publications at ICRA, CoRL and other top-tier conferences. We collaborate with top academic labs, combining the best of an academic environment with product-driven research.

Responsibilities

• Design and implement new capabilities in a variety of topics related to robotic manipulation, including imitation learning and reinforcement learning, deep learning and pose estimation with vision, tactile and other sensing modalities, sim2real transfer
• Communicate ideas, problems, and results with the team
• Collaborate with researchers and developers in the team
• Co-publish with Autodesk Robotics and AI Lab collaborators
• Read papers and perform literature reviews
• Evaluate existing algorithms and reproduce results on specific datasets

Minimum Qualifications

• Full-time student pursuing an MS or Ph.D. in Robotics, Computer Science, Computer Vision, Machine Learning, Mechanical Engineering, or an affiliated discipline in an accredited program with at least one academic term to complete post-internship
• Extensive experience in one or more of the following areas: robotic manipulation, machine learning, deep learning, computer vision
• Excellent Programming and software development skills, fluent in Python and C++
• Proficient with deep learning platforms and libraries
• Prior experience developing and working with robotics and simulation software
• Track record of research publications
• An excellent communicator and a team player

Preferred Qualifications

• Practical experience with integrating robots and 2D/3D vision, tactile sensing, and F/T sensing for contact-based manipulation tasks
• Practical experience with deployment both in simulation and on real hardware