Research Scientist/Engineer, Mobile Manipulation - Behaviors

The team will be focused on heavily leveraging machine learning to marry perception, prediction, and action to produce robust, reactive, coordinated robot behaviors, bootstrapping from simulation, leveraging large amounts of data, and adapting in real-world scenarios. TRI has the runway, roadmap, and expertise to transition the technology development to a product that impacts the lives of millions of people. Apply to join a fast-moving team that demands high-risk innovation and learning from failures, using rigorous processes to identify key technologies, develop a robust, high-quality system, and quantitatively evaluate performance. As part of the team, you will be surrounded and supported by the significant core ML, cloud, software, and hardware expertise at TRI, and be a part of TRI's positive and diverse culture. Responsibilities

Develop, integrate, and deploy algorithms linking perception to autonomous robot actions, including manipulation, navigation, and human-robot interaction. Invent and deploy innovative solutions at the intersection of machine learning, mobility, manipulation, human interaction, and simulation for performing useful, human-level tasks, in and around homes. Invent novel ways to engineer and learn robust, real-world behaviors, including using optimization, planning, reactive control, self-supervision, active learning, learning from demonstration, simulation and transfer learning, and real-world adaptation. Be part of a team that fields systems, performs failure analysis, and iterates on improving performance and capabilities. Follow software practices that produce maintainable code, including automated testing, continuous integration, code style conformity, and code review. Qualifications

M.S. or Ph.D. in an engineering-related field. A strong track record in inventing and deploying innovative autonomous behaviors for robotic systems in real-world environments. Expertise and experience in areas such as reactive control, trajectory optimization, coordinated whole-body control, dexterous manipulation, arm motion planning, grasp planning, navigation, and human interaction. Expertise and experience in applying machine learning to robotics, including areas such as reinforcement, imitation, and transfer learning. Strong software engineering skills, preferably in C++, and analysis and debugging of autonomous robotic systems. A team player with strong communication skills, and a willingness to learn from others and contribute back to the robotics community with publications or open source code. Passionate about seeing robotics have a real-world, large-scale impact.

#J-18808-Ljbffr