Projects

Autonomous vehicles have tremendous social and economic values for society. But before we can see large-scale deployment, its perception systems need to make significant progress in robustness and generalization capability. To address these challenges, we bring context, the semantic meaning into the robot perception. Our approach is to conduct research on our full-scale testing vehicles, our living laboratory. We evaluate the state-of-the-art algorithms, search for and address the challenges we found in real-world deployment. Such challenges include long term tracking and prediction of road users, dynamic scene modeling and dynamic planning. Read more.

Interactions in dynamic environments require planning of actions to allow for intelligent interaction for manipulation of objects. Dynamic interaction with the environment not only includes basic mobility but also the ability to modify the environment through manipulation for assembly, logistics and simple clean-up. The research primarily focuses on task and motion planning for reliable and efficient manipulation actions in dynamic environments for home robots. It includes both basic physical interaction and mobile manipulation. For handling of unexpected objects and situations, there is also a need to consider ad-hoc planning to recover from surprises or un-modelled events.

Safety-critical systems often require human-in-the loop architecture due to the high consequences of error or failure. The performance of these systems, unlike the success of fully autonomous platforms, depends on not only machine capabilities but also the efficacy of human operators. We use surgical robotics platforms from across the autonomy spectrum - completely teleoperated to fully autonomous - to examine human operator performance through biometric analysis as well as autonomous platform capabilities through task environment perception and reasoning. We aim to develop generalizable methods to understand, predict, and enhance the success rates of human-in-the-loop robotic systems participating in safety-critical scenarios.

Many tasks in the real world require teams composed of multiple robots to work together. For example, in the security domain, multiple robots can continuously monitor a physical perimeter to detect intrusions. Solving multi-robot problems, however, introduces several key challenges, such as learning and acting in the presence of other actors who may introduce added complexity by altering their behaviors. This research area spans a large spectrum from traditional game-theoretic methods, to the application of multi-agent reinforcement learning, to develop solutions to multi-robot tasks such as multi-robot patrolling and pursuit-evasion.

A key feature of modern robots operating in human-centric environments is the ability to estimate scene layout, and also associate semantics with scene components, to allow for contextual interaction. Intelligent robots for both in-door and out-door environments, heavily require interpretation of the surrounding to facilitate interaction and planning. We aim to leverage foundational concepts of geometric localization and mapping from classical robotics, along with recent developments in learning-based techniques for retrieving context and scene knowledge, in order to develop smart algorithms for tasks such as semantic scene understanding, mapping, and robot navigation.