This project is exploring the use of crowd-sourcing, or citizen science, to produce a large database of analyzed human manipulation video. Every human is an expert on human manipulation. Harnessing this expertise has the potential to radically transform our knowledge of manipulation. A large analyzed video database directly serves several important goals of robotics, including autonomous robotic manipulation and recognition of human behavior. This new approach is in its earliest stages. The project goals are to explore the new approach, identify problems, assess the value, refine the vision, and formulate plans. Activities include development of pilot interfaces, testing different approaches to user training, and developing approaches to the filtering and aggregation of results. The ultimate impact will be a broader scientific understanding of human manipulation, and a large dataset to support research in robotic manipulation and human behavior recognition. Results will be disseminated through publication of discoveries related to human manipulation, open access to the database, and open access to the crowd-sourcing interface and related software.
