ICP Localization and Walking Experiments on a TALOS Humanoid Robot

Lasguignes, T.; Maroger, Isabelle; Fallon, Maurice; Ramezani, Milad; Marchionni, Luca; Stasse, Olivier; Mansard, Nicolas; Watier, Bruno

doi:10.1109/icar53236.2021.9659474

Cited by 4 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fig. 2: Intensity image reconstructed, the data is from an experiment of [1], it has been divided in two parts for visibility purposes.…”

Section: Intensity-based Methodsmentioning

confidence: 99%

“…A case is considered successful if the error in translation is below 10cm and the error in rotation is below 5 • . These thresholds have been fixed relatively to the problematic: initializing the localization system presented in [1]. We experimentaly determined that the localization mechanism needs an initialization with 50cm of translation tolerance and 30 • of rotation in the ⃗ z-axis.…”

Section: B Ransac Coarse Estimationmentioning

confidence: 99%

“…In this context, few textures are present and many unusual large objects are present in the environment. Still it is possible to apply a LiDAR-based localization system [1], implemented on a Talos robot [2], for allowing a precise estimation of the robot localization in a known environment. A limitation of this system is the need for an estimate of the robot initial pose.…”

Section: Introductionmentioning

confidence: 99%

“…Thus, the pose M p 0 of the robot in the environment when the localization system is started needs to be estimated in order to initialize the SLAM system by providing the estimation in the known world. In the experiment presented in [1], an approximation of the Mocap estimate, that was used as ground truth, was used as the initial pose.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

LiDAR-Based Localization System for Kidnapped Robots

Lasguignes,

Gobin,

Stasse

2023

2023 Seventh IEEE International Conference on Robotic Computing (IRC)

View full text Add to dashboard Cite

Place recognition is the ability to recognize previously seen places in the world. When the environment is known, the robot may localise itself when it starts and whenever it needs to verify where it is. We propose a solution to implement place recognition capability using a geometric representation of the environment build with a LiDAR. Nowadays, large Field Of View LiDARs allows to get a dense and precise representation of the environment. Assuming that a 3D map of the environment is available, we propose to build a compressed codebook based on FPFH descriptors. The codebook is then used to find the robot localization with one LiDAR image. The system has been tested on real and simulated measurements and shows promising results. The pose estimation can be thoroughly enhanced with point cloud registration methods.

show abstract

“…Fig. 2: Intensity image reconstructed, the data is from an experiment of [1], it has been divided in two parts for visibility purposes.…”

Section: Intensity-based Methodsmentioning

confidence: 99%

Section: B Ransac Coarse Estimationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

LiDAR-Based Localization System for Kidnapped Robots

Lasguignes,

Gobin,

Stasse

2023

2023 Seventh IEEE International Conference on Robotic Computing (IRC)

View full text Add to dashboard Cite

show abstract

“…Very often, MoCap is used as precise ground truth to determine the position and orientation of the floating base of a humanoid robot. For example, MoCap has been used to evaluate different state estimation approaches based on proprioceptive sensors [5], LiDAR and kinematic-inertial data fusion [6], as well as LiDAR fused with visual-inertial odometry [7]. Less frequently, external motion capture systems have been used to provide state feedback to the control loops of legged robots.…”

Section: Introductionmentioning

confidence: 99%

Experimental Investigations into Using Motion Capture State Feedback for Real-Time Control of a Humanoid Robot

Popescu

Mronga

Bergonzani

et al. 2022

Sensors

View full text Add to dashboard Cite

Regardless of recent advances, humanoid robots still face significant difficulties in performing locomotion tasks. Among the key challenges that must be addressed to achieve robust bipedal locomotion are dynamically consistent motion planning, feedback control, and state estimation of such complex systems. In this paper, we investigate the use of an external motion capture system to provide state feedback to an online whole-body controller. We present experimental results with the humanoid robot RH5 performing two different whole-body motions: squatting with both feet in contact with the ground and balancing on one leg. We compare the execution of these motions using state feedback from (i) an external motion tracking system and (ii) an internal state estimator based on inertial measurement unit (IMU), forward kinematics, and contact sensing. It is shown that state-of-the-art motion capture systems can be successfully used in the high-frequency feedback control loop of humanoid robots, providing an alternative in cases where state estimation is not reliable.

show abstract

Neural network-based robot localization using visual features

Trujillo-Romero

2024

ings

View full text Add to dashboard Cite

This paper outlines the development of a module capable of constructing a map-building algorithm using inertial odometry and visual features. It incorporates an object recognition module that leverages local features and unsupervised artificial neural networks to identify non-dynamic elements in a room and assign them positions. The map is modeled using a neural network, where each neuron corresponds to an absolute position in the room. Once the map is constructed, capturing just a couple of images of the environment is sufficient to estimate the robot's location. The experiments were conducted using both simulation and a real robot. The Webots environment with the virtual humanoid robot NAO was used for the simulations. Concurrently, results were obtained using a real NAO robot in a setting with various objects. The results demonstrate notable precision in localization within the two-dimensional maps, achieving an accuracy of ± (0.06, 0.1) m in simulations contrasted with the natural environment, where the best value achieved was ± (0.25, 0.16) m.

show abstract

ICP Localization and Walking Experiments on a TALOS Humanoid Robot

Cited by 4 publications

References 15 publications

LiDAR-Based Localization System for Kidnapped Robots

LiDAR-Based Localization System for Kidnapped Robots

Experimental Investigations into Using Motion Capture State Feedback for Real-Time Control of a Humanoid Robot

Neural network-based robot localization using visual features

Contact Info

Product

Resources

About