简介:Robotics are increasing being use for manufacturing, assembly, warehouse automation, and service industries. However, current robots have limited capabilities in terms of handling new environments or working next to humans or with the humans. In this talk, we highlight some challenges in terms of developing motion and task planning capabilities that can enable robots to operate automatically in such environments. These include real-time planning algorithms that can also integrate with current sensor and perception techniques. We present new techniques for realtime motion planning and how they can be integrated with vision-based algorithms for human action prediction as well as natural language processing. The resulting approaches use a combination of ideas from AI planning, topology, optimization, computer vision, machine learning, natural language processing, and parallel computing. We also demonstrate many applications in terms of autonomous picking, avoiding human obstacles, and operating as cobots.