• Publications
  • Influence
Robust visual inertial odometry using a direct EKF-based approach
In this paper, we present a monocular visual-inertial odometry algorithm which, by directly using pixel intensity errors of image patches, achieves accurate tracking performance while exhibiting aExpand
Iterated extended Kalman filter based visual-inertial odometry using direct photometric feedback
TLDR
Experimental results show that robust localization with high accuracy can be achieved with this filter-based framework, and there is no time-consuming initialization procedure and pose estimates are available starting at the second image frame. Expand
Learning agile and dynamic motor skills for legged robots
TLDR
This work introduces a method for training a neural network policy in simulation and transferring it to a state-of-the-art legged system, thereby leveraging fast, automated, and cost-effective data generation schemes. Expand
Control of a Quadrotor With Reinforcement Learning
TLDR
A method to control a quadrotor with a neural network trained using reinforcement learning techniques and a new learning algorithm that differs from the existing ones in certain aspects is presented, found that it is more applicable to controlling a Quadrotor than existing algorithms. Expand
ANYmal - a highly mobile and dynamic quadrupedal robot
TLDR
Anymal, a quadrupedal robot that features outstanding mobility and dynamic motion capability, is introduced with a focus on outdoor suitability, simple maintenance, and user-friendly handling to enable future operation in real world scenarios. Expand
Gait and Trajectory Optimization for Legged Systems Through Phase-Based End-Effector Parameterization
We present a single trajectory optimization formulation for legged locomotion that automatically determines the gait sequence, step timings, footholds, swing-leg motions, and six-dimensional bodyExpand
Kinect v2 for mobile robot navigation: Evaluation and modeling
TLDR
The results of calibrating the intrinsic camera parameters are presented and the minimal range of the depth sensor is examined, and empirically derived noise models for the Kinect v2 sensor are introduced in both axial and lateral directions. Expand
Per-Contact Iteration Method for Solving Contact Dynamics
TLDR
This letter introduces a new iterative method for contact dynamics problems based on an efficient bisection method which iterates over each contact that can simulate an 18-DOF robot more than thousand times faster than the real time. Expand
State Estimation for Legged Robots - Consistent Fusion of Leg Kinematics and IMU
TLDR
A state estimation framework for legged robots that allows estimating the full pose of the robot without making any assumptions about the geometrical structure of its environment is introduced by means of an Observability Constrained Extended Kalman Filter that fuses kinematic encoder data with on-board IMU measurements. Expand
ANYmal - a highly mobile and dynamic quadrupedal robot
This paper introduces ANYmal, a quadrupedal robot that features outstanding mobility and dynamic motion capability. Thanks to novel, compliant joint modules with integrated electronics, the 30 kg,Expand
...
1
2
3
4
5
...