Towards Goal-Driven Visually Grounded Dialog Agents
Abstract: Communication between human users and artificial intelligences is essential for human-AI cooperative tasks. For these collaborations to extend into real environments, artificial agents must be able to perceive their environment (visually, aurally, tactilely, etc.) and to communicate with humans about it in order to accomplish mutual goals. For example, a user might talk with [...]
Carnegie Mellon University
Exploiting Redundancy for Learning Visual Representations
Abstract: Our visual world is highly structured and the visual data is highly redundant. In recent years, the computer vision field has been transformed by the success of Convolutional Neural Networks (ConvNets). However, the structure and redundancy in visual data has not been well explored in deep learning. The benefits of exploring data redundancy are [...]
Carnegie Mellon University
Adaptive Motion Planning
Abstract: Mobile robots are increasingly being deployed in the real world in response to a heightened demand for applications such as transportation, delivery and inspection. The motion planning systems for these robots are expected to have consistent performance across the wide range of scenarios that they encounter. While state-of-the-art planners, with provable worst-case guarantees, can [...]
Robots and the Smart Home
Abstract Home robots, such as the iRobot Roomba vacuuming robot, have been welcomed into millions of homes around the world and are hard at work every day helping people to get more done. iRobot is the market leader in home robotics and is at the forefront in developing technologies for practical robots, including visual SLAM, [...]
Long Duration Autonomy With Applications to Persistent Environmental Monitoring
Abstract: By now, we have a fairly good understanding of how to design coordinated control strategies for making teams of mobile robots achieve geometric objectives in a distributed manner, such as assembling shapes or covering areas. But, the mapping from high-level tasks to geometric objectives is not well understood. In this talk, we investigate this [...]
Faculty Candidate Talk: Extreme Motions in Natural and Synthetic Systems
Areas of Interest: Extreme motions of small-scale natural and synthetic systems Abstract: Small organisms can achieve extraordinary accelerations, speeds, and forces repeatedly throughout their lifespan with minimal costs. For example, bacteria can effectively swim in low Reynolds number environments, rotating their flagella at 100 Hz; mantis shrimp break clam shells with a single strike, [...]
Faculty Candidate Talk: Design and Evaluation of Everyday Interactive Robots
Areas of Interest: Human-Computer Interaction and Robotics Host: Aaron Steinfeld Admin Contact: Peggy Martin pm1e@andrew.cmu.edu As robots appear in more everyday environments, they will have new opportunities to enhance the lives of the people around them. Despite this potential gain, modern robots lack many of the necessary skills to effectively interact with people. In particular, almost all [...]
Marine Robotics: Planning, Decision Making, and Learning
Abstract: Underwater gliders, propeller-driven submersibles, and other marine robots are increasingly being tasked with gathering information (e.g., in environmental monitoring, offshore inspection, and coastal surveillance scenarios). However, in most of these scenarios, human operators must carefully plan the mission to ensure completion of the task. Strict human oversight not only makes such deployments expensive and [...]
Faculty Candidate: David Braun
Areas of interest: Robotics, Optimal Control, System Dynamics, Impedance Control, Variable Impedance Actuators Host: Hartmut Geyer Admin Contact: Keyla Cook keylac@andrew.cmu.edu
Carnegie Mellon University
Kernel and Moment based Prediction and Planning: Applications to Robotics and Natural Language Processing
Abstract This thesis focuses on moment and kernel-based methods for applications in Robotics and Natural Language Processing. Kernel and moment-based learning leverage information about correlated data that allow the design of compact representations and efficient learning algorithms. We explore kernel algorithms for planning by leveraging inherently continuous properties of reproducing kernel Hilbert spaces. We introduce [...]