6 papers
A Smooth Representation of Belief over SO(3) for Deep Rotation Learning with Uncertainty
Valentin Peretroukhin, Matthew Giamou, David M. Rosen +3
Accurate rotation estimation is at the heart of robot perception tasks such as visual odometry and object pose estimation. Deep neural networks have provided a new way to perform t…
Inverse Kinematics for Serial Kinematic Chains via Sum of Squares Optimization
Filip Maric, Matthew Giamou, Soroush Khoubyarian +2
Inverse kinematics is a fundamental problem for articulated robots: fast and accurate algorithms are needed for translating task-related workspace constraints and goals into feasib…
Probabilistic Regression of Rotations using Quaternion Averaging and a Deep Multi-Headed Network
Valentin Peretroukhin, Brandon Wagstaff, Matthew Giamou +1
Accurate estimates of rotation are crucial to vision-based motion estimation in augmented reality and robotics. In this work, we present a method to extract probabilistic estimates…
Sparse Bounded Degree Sum of Squares Optimization for Certifiably Globally Optimal Rotation Averaging
Matthew Giamou, Filip Maric, Valentin Peretroukhin +1
Estimating unknown rotations from noisy measurements is an important step in SfM and other 3D vision tasks. Typically, local optimization methods susceptible to returning suboptima…
Certifiably Globally Optimal Extrinsic Calibration from Per-Sensor Egomotion
Matthew Giamou, Ziye Ma, Valentin Peretroukhin +1
We present a certifiably globally optimal algorithm for determining the extrinsic calibration between two sensors that are capable of producing independent egomotion estimates. Thi…
Near-Optimal Budgeted Data Exchange for Distributed Loop Closure Detection
Yulun Tian, Kasra Khosoussi, Matthew Giamou +2
Inter-robot loop closure detection is a core problem in collaborative SLAM (CSLAM). Establishing inter-robot loop closures is a resource-demanding process, during which robots must…