Enrollment may be limited due to laboratory capacity preference to Course 2 majors and minors. Students taking graduate version complete additional assignments. Group term project builds intelligent robots for specific applications of interest. Weekly laboratories include brushless DC motor control, design and fabrication of robotic arms and vehicles, robot vision and navigation, and programming and system integration using Robot Operating System (ROS). Second half of course focuses on algorithmic thinking and computation, computer vision and perception, planning and control for manipulation, localization and navigation, machine learning for robotics, and human-robot systems. Emphasizes physical understanding of robot kinematics and dynamics, differential motion and energy method, design and control of robotic arms and mobile robots, and actuators, drives, and transmission. ![]() Our algorithms automatically leverage temporal and spatial models of activities to perform early classification of human activities and quickly update robot task plans.Fall/Spring | Undergraduate | 12 Units | Prereq: 2.004Ĭross-disciplinary studies in robot mechanics and intelligence. Robots also need to make quick adjustments to their plans based on continually updating predictions of human actions.There are no prior task assignment and sequencing algorithms that scale to multi-agent factory size problems and support on-the-fly scheduling in the presence of temporal and spatial proximity constraints. The robot must predict detailed space-time trajectories of human actions for short and long timescales (<1s to 10-20s) to react appropriately. No existing single technique provides accurate predictions over short and long time horizons, in most scenarios. Prior activity recognition approaches are designed and tuned for specific motions or tasks. However, it is challenging for a machine to monitor a human's real-time progress through a plan. Once a team has refined their plan, the members must coordinate while executing the plan. Our models and algorithms for jointly optimizing human-robot team performance are derived based on insights from effective human team training processes, including cross-training and perturbation training. Our approach to policy learning is made possible with little data and no environment/expert emulator, through insight from models of human cognition. An effective machine teammate must co-adapt its collaboration strategies to support the human's learning process. People adapt their strategies through continued interactions with teammates. There is typically little data available to learn from, no environment simulator/expert emulator, and many approaches to learning require regression through a very large state space.įurther, machine learning through remote observation is not sufficient to refine a human-robot team plan. With support from the Defense Advanced Research Projects Agency (DARPA), we are building a telerobotic system that has two parts: a humanoid capable of nimble, dynamic behaviors, and a new kind of two-way human-machine interface that sends your motions to the robot and the robot’s motions to you. However there are no prior effective techniques for learning human task allocation and scheduling policies from human demonstration. The MIT Cheetah I, a planar quadruped platform for high-speed running, achieves these tasks with a speed of 3.2 m/s (Froude number of 2.1) on a treadmill. These challenges motivate a machine learning approach for refining idealized shared plans for real contexts. This paper presents a demonstration of the trot-to-gallop transition and subsequent stable gallop in a robotic quadruped. ![]() And people find it difficult to explicitly communicate how the team adapts their idealized plan to myriad real-world situations. rules and heuristics for task allocation, synchronization, timing) based on many factors including past experience, workload or personal preference. People change their collaboration strategies (i.e. But the team rarely follows the plan exactly. ![]() The purpose of team planning is to form an idealized shared plan.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |