Corpus ID: 235899175

VILENS: Visual, Inertial, Lidar, and Leg Odometry for All-Terrain Legged Robots

  title={VILENS: Visual, Inertial, Lidar, and Leg Odometry for All-Terrain Legged Robots},
  author={David Wisth and Marco Camurri and Maurice F. Fallon},
We present VILENS (Visual Inertial Lidar Legged Navigation System), an odometry system for legged robots based on factor graphs. The key novelty is the tight fusion of four different sensor modalities to achieve reliable operation when the individual sensors would otherwise produce degenerate estimation. To minimize leg odometry drift, we extend the robot's state with a linear velocity bias term which is estimated online. This bias is only observable because of the tight fusion of this… Expand
Balancing the Budget: Feature Selection and Tracking for Multi-Camera Visual-Inertial Odometry
A multi-camera visual-inertial odometry system based on factor graph optimization which estimates motion by using all cameras simultaneously while retaining a fixed overall feature budget and using a smaller set of informative features to maintain the same tracking accuracy while reducing backend optimization time is presented. Expand


Robust Legged Robot State Estimation Using Factor Graph Optimization
A factor graph optimization method is presented which tightly fuses and smooths inertial navigation, leg odometry and visual odometry to reduce the dependency on foot contact classifications, which fail when slipping, and to reduce position drift during dynamic motions such as trotting. Expand
Pronto: A Multi-Sensor State Estimator for Legged Robots in Real-World Scenarios
The proposed estimation system, called Pronto, is an Extended Kalman Filter that fuses IMU and Leg Odometry sensing for pose and velocity estimation that can integrate pose corrections from visual and LIDAR and odometry to correct pose drift in a loosely coupled manner. Expand
Online LiDAR-SLAM for Legged Robots with Robust Registration and Deep-Learned Loop Closure
A 3D factor-graph LiDAR-SLAM system which incorporates a state-of-the-art deeply learned feature-based loop closure detector to enable a legged robot to localize and map in industrial environments is presented. Expand
Legged Robot State-Estimation Through Combined Forward Kinematic and Preintegrated Contact Factors
Preliminary experiments show that using the proposed method in addition to IMU decreases drift and improves localization accuracy, suggesting that its use can enable successful recovery from a loss of visual tracking. Expand
Probabilistic Contact Estimation and Impact Detection for State Estimation of Quadruped Robots
This paper focuses on the development of a robust Leg Odometry module, which does not require contact sensors and estimates the probability of reliable contact and detects foot impacts using internal force sensing and shows how this approach can reach comparable performance to systems with foot sensors. Expand
LOCUS: A Multi-Sensor Lidar-Centric Solution for High-Precision Odometry and 3D Mapping in Real-Time
This work presents a high-precision lidar odometry system to achieve robust and real-time operation under challenging perceptual conditions, and provides an accurate multi-stage scan matching unit equipped with an health-aware sensor integration module for seamless fusion of additional sensing modalities. Expand
State estimation for legged robots on unstable and slippery terrain
The key idea is to extract information from the kinematic constraints given through the intermittent contacts with the ground and to fuse this information with inertial measurements to design an unscented Kalman filter based on a consistent formulation of the underlying stochastic model. Expand
LIO-SAM: Tightly-coupled Lidar Inertial Odometry via Smoothing and Mapping
We propose a framework for tightly-coupled lidar inertial odometry via smoothing and mapping, LIO-SAM, that achieves highly accurate, real-time mobile robot trajectory estimation and map-building.Expand
Probabilistic Terrain Mapping for Mobile Robots With Uncertain Localization
A novel terrain mapping method, which bases on proprioceptive localization from kinematic and inertial measurements only, which yields a probabilistic terrain estimate as a grid-based elevation map including upper and lower confidence bounds. Expand
On State Estimation for Legged Locomotion Over Soft Terrain
It is demonstrated that soft terrain negatively affects state estimation for legged robots and that the state estimates have a noticeable drift over soft terrain compared to rigid terrain. Expand