Title: Environment Generalization in Deep Reinforcement Learning Abstract: A key challenge in deep reinforcement learning (RL) is environment generalization: a policy trained to solve a task in one environment often fails to solve the same task in a slightly different test environment. In this work, we propose the ``Environment-Probing'' Interaction (EPI) policy, which allows the agent [...]

Title: Human Torso Pose Forecasting for the Real World   Abstract: Anticipatory human intent modeling is important for robots operating alongside humans in dynamic or crowded environments. Humans often telegraph intent through posture cues, such as torso or head cues. In this paper, we describe a computationally lightweight approach to human torso pose recovery and forecasting [...]

Title: Object-level visual SLAM for plant modeling   Abstract: A 3D model that can capture the finer details of the plant structure as well as the overall field statistics, plays an important role in automating agriculture. However, modeling and mapping an agricultural field is challenging due to dynamics, illumination conditions and limited texture inherent in an outdoor environment. We propose a pipeline that combines the recent [...]

Title: Behavior planning at roundabouts   About the talk: Roundabouts or traffic circles represent a significant portion of unsignalized intersections commonly found in urban and rural roads and pose a specific challenge for autonomous or self-driving cars. In this work, we present model-free techniques that allow a self-driving car to navigate a roundabout safely.  We [...]

Title: Towards retinal membrane peeling with a handheld robotic instrument   Abstract: Vitreoretinal surgery procedures demand high precision and have to be performed with limited visualization and access. One such procedure is membrane peeling, which involves peeling of the 5-10 µm thick internal limiting membrane around macular holes. Using virtual fixtures in conjunction with robotic [...]

Title: Spatiotemporal Modeling using Recurrent Neural Processes   Abstract: Spatiotemporal processes, such as temperature in an area, motion of a vehicle, etc., depend on the spatial features of the underlying phenomena as well as time. Developing models that can estimate both mean and uncertainty associated with the prediction is important for building robust systems capable of [...]

Title: Localization and Active Exploration in Indoor Underwater Environments Abstract: Autonomous underwater vehicles have the potential to inspect and map indoor underwater environments, such as spent nuclear fuel pools and ship ballast tanks. Towards this, the thesis makes contributions in the domains of visual localization and active SLAM for underwater environments. In the first work, [...]

Title: Multi-Sensor Fusion for Robust Simultaneous Localization and Mapping   Abstract:  Simultaneous Localization and Mapping (SLAM) consists of the estimation of the state of the robot, and the reconstruction of the surrounding environment simultaneously. Over the last few decades, numerous state-of-the-art SLAM algorithms are proposed and frequently utilized in the robotics community. However, a SLAM algorithm [...]

Title: State Estimation for Legged Robots using Proprioceptive Sensors   Abstract:  Mobile robots need good estimates of their state to perform closed-loop control in structured and unstructured environments. A number of existing algorithms rely on data fusion from multiple sensors to compute these estimates. This work focuses on state estimation using sensors which only measure [...]