Publications

In this paper, we present ST-VIO, a novel approach which tightly fuses a single-track dynamics model for wheeled ground vehicles with visual inertial odometry. Our method calibrates and adapts the dynamics model online and facilitates accurate forward prediction conditioned on future control inputs.

We propose E-LnR, an event camera-based approach for reconstructing non-rigid deformable objects in the low rank parametrized space. This is a journal extension of our BMVC 2022 paper.

In this paper, we propose a novel approach for combining VIO with leg odometry in an extended Kalman filter based state estimator. We integrate this lightweight estimation framework with a nonlinear model predictive controller and show successful implementation of a set of agile locomotion behaviors on the Solo robot.

We develop a probabilistic, terrain- and robot-aware forward dynamics model, termed TRADYN, which is able to adapt to the above-mentioned variations.

In this paper, we propose a novel approach for VIO with stereo cameras which integrates and calibrates the velocity-control based kinematic motion model of wheeled mobile robots online. We use radial basis function (RBF) kernels to compensate for the time delay and deviations between control commands and actual robot motion. The motion model is calibrated online by the VIO system and can be used as a forward model for motion control and planning.

We propose a novel approach for reconstructing fast non-rigid object deformations using measurements from event-based cameras. Under the assumption of a static background, where all events are generated by the motion, our approach estimates the deformation of objects from events generated at the object contour in a probabilistic optimization framework.

In this work, we present an approach for 6 degree-of-freedom (6-DoF) object motion tracking that combines measurements of event and frame-based cameras. We formulate tracking from high rate events with a probabilistic generative model of the event measurement process of the object. On a second layer, we refine the object trajectory in slower rate image frames through direct image alignment.