She’s a researcher at the Massachusetts Institute of Technology (MIT) Media Lab, where she investigates social robotics and conducts experimental studies on … The lack of radio communication forces all human control to pass through high latency, low-bandwidth acoustic channels or hardwire tethers. Theoretical foundations: we tackle fundamental problems in SLAM that are applicable across domains such as robustness, scalability, consistency, map representation and others. On all but the most straightforward problems, however, even the best planning algorithms still aren’t as effective as human beings with a particular aptitude for problem-solving — such as MIT students.Today’s robots are awkward co-workers because they are often unable to predict what humans need. Humans, by contrast, are good at inferring patterns from just a few examples.In a paper appearing at the Neural Information Processing Society’s conference next week, CSAIL researchers present a new system that bridges these two ways of processing information, so that humans and computers can collaborate to make better decisions.Predicting Human Motion for Fluid Human-Robot TeamingIntelligent Modality Selection for Navigation SystemsLearning complex task structures from demonstrationsApprenticeship Scheduling: Learning to Schedule From Human ExpertsRobots that collaborate with humans to form team plans Robots that Quickly Adjust Team Plans to DisturbanceAdding a splash of human intuition to planning algorithmsAdding a splash of human intuition to planning algorithms communications-denied environments. Paul Newman (Director of Oxford Robotics Institute, U. of Oxford) Edwin Olson (Professor at U of Michigan) Liam Paull (Assistant Professor at the University of Montreal) Georgios Papadopoulos (PhD student in the MIT Department of Mechanical Engineering) Sudeep Pillai (Researcher at the Toyota Research Institute) David Rosen (Postdoc at MIT LIDS) We are building systems that robustly understand natural language commands produced by untrained users. With unmanned aerial vehicles (UAVs) becoming more prolific and capable, and regulations evolving, their eventual operation in urban environments seems all but certain. A robot designed to interact naturally with humans must be able to understand instructions without requiring the person to speak in any special way.


We also develop algorithms that enable robots to make fast adjustments to team plans in response to disturbances — to “play the game” with people.
Our project focuses on developing a general human motion prediction framework that can be applied in a variety of domains, ranging from manufacturing to space robotics, in order to improve the safety and efficiency of human-robot interaction.

Alternatively, natural language provides a rich, intuitive and flexible medium for humans and robots to communicate information. Natural language is an intuitive and flexible modality for human-robot interaction. Mature mapping techniques now allow practitioners to reliably and consistently generate 2-D and 3-D maps of objects, office buildings, city blocks and metropolitan areas with a comparatively small number of errors. joint position and torque sensors, imu's etc. I’m turning 90 degrees right.” “After advancing 4 feet I’ve encountered a wall.” And so on.Computers, of course, have no trouble filing this information away until they need it. The absence of GPS and high-bandwidth Our research goals are to build unmanned vehicles that can fly without GPS through unmapped indoor environments, robots that can drive through unmapped cities, and to build social robots that can quickly learn what people want without being annoying or intrusive.

We have shown that the POMDP model parameters can be incorporated as additional hidden states in a larger 'model-uncertainty' POMDP, and we have developed an approximate algorithm for planning in the induced `model-uncertainty' POMDP. We plan to address the problem of learning a meaningful feature representation of underwater images using deep learning. one of the group leads' people pages, where you can reach out to them directly.Computer Science & Artificial Intelligence LaboratoryWe build unmanned vehicles that can fly and drive without maps or GPS.We build unmanned vehicles that can fly and drive without maps or GPS.Our goal is to develop methods for a mobile robot to reason about volumetric spatial uncertainty of objects in its environment.

Paul Newman (Director of Oxford Robotics Institute, U. of Oxford) Edwin Olson (Professor at U of Michigan) Liam Paull (Assistant Professor at the University of Montreal) Georgios Papadopoulos (PhD student in the MIT Department of Mechanical Engineering) Sudeep Pillai (Researcher at the Toyota Research Institute) David Rosen (Postdoc at MIT LIDS) Robot manipulators largely rely on complete knowledge of object geometry in order to plan their motion and compute successful grasps. People, including doctors, nurses, and military personnel, often learn their roles in complex organizations through a training and apprenticeship process. Further work hopes to leverage a library of precomputed wind fields to find a wind field covariance estimate within a region. Result of running HDP spatiotemporal topic model on image data from marine robot mission. Mapping as a research problem has received considerable attention in robotics recently. In a pair of new papers, CSAIL researchers demonstrate a robot that, by learning from human workers, can help assign and schedule tasks in fields ranging from medicine to the military.Autonomous robots performing a joint task send each other continual updates: “I’ve passed through a door and am turning 90 degrees right.” “After advancing 2 feet I’ve encountered a wall. Some of our recent work has involved using machine learning to capture (at training time) the local environmental geometry so that we may predict (at run time) the probability that taking an action that guides it into unknown space will cause the robot to collide.