Hardware-Accelerated Mars Sample Localization Via Deep Transfer Learning From Photorealistic Simulations

Castilla-Arquillo, Raul; Pérez-del-Pulgar, Carlos Jesús; Delgado, Gonzalo Jesús Paz; Gerdes, Levin

doi:10.1109/lra.2022.3219306

Cited by 2 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, two additional subsystems were integrated in the platform, apart from the presented MWMP and replanning algorithms. First, an autonomous sample detection and localization subsystem based on Convolutional Neural Networks (CNNs), which uses the LocCam stereo images to locate the sample tube with an average under 5 cm position and 5 • orientation errors [28]. Second, a visual odometry algorithm for the platform localization, using the LocCam stereo camera and the IMU, with 7.5 % average localization drift in position and less than 2 • orientation error [29].…”

Section: Methodsmentioning

confidence: 99%

Multi-stage warm started optimal motion planning for over-actuated mobile platforms

Delgado

Pérez-del-Pulgar

Azkarate

et al. 2023

Intel Serv Robotics

Self Cite

View full text Add to dashboard Cite

This work presents a computationally lightweight motion planner for over-actuated platforms. For this purpose, a general state-space model for mobile platforms with several kinematic chains is defined, which considers dynamics, nonlinearities and constraints. The proposed motion planner is based on a sequential multi-stage approach that takes advantage of the warm start on each step. Firstly, a globally optimal and smooth 2D/3D trajectory is generated using the Fast Marching Method. This trajectory is fed as a warm start to a sequential linear quadratic regulator that is able to generate an optimal motion plan without constraints for all the platform actuators. Finally, a feasible motion plan is generated considering the constraints defined in the model. In this respect, the sequential linear quadratic regulator is employed again, taking the previously generated unconstrained motion plan as a warm start. The motion planner has been deployed into the Exomars Testing Rover of the European Space Agency. This rover is an Ackermann-capable planetary exploration testbed that is equipped with a robotic arm. Several experiments were carried out demonstrating that the proposed approach speeds up the computation time and increases the success ratio for a martian sample retrieval mission, which can be considered as a representative use case of goal-constrained trajectory generation for an over-actuated mobile platform.

show abstract

Section: Methodsmentioning

confidence: 99%