Explore projects

Elevation Mapping on GPU.

Official implementation of the paper "A Simple yet Effective Test-Time Adaptation for Zero-Shot Monocular Metric Depth Estimation" accepted to IROS 2025. In this paper, we propose to rescale Depth Anything predictions using 3D points provided by sensors or techniques such as low-resolution LiDAR or structure-from-motion with poses given by an IMU. This approach avoids fine-tuning and preserves the generalizing power of the original depth estimation model while being robust to the noise of the sparse depth, of the camera-LiDAR calibration or of the depth model.

ROS package providing a simple interface to move a robot arm using the Moveit! motion planning framework

ROS Package implementing several acoustic measurements routines based on the use of a robot arm, and different kind of microphones.

ROS Package implementing a 3D scan procedure based on the use of a robot arm, and a depth estimation tool (Intel RealSense d435 or Hokuyo LIDAR).

A ROS-based kinematic calibration tool for serial robots: the unberdening of a crucial task

Elevation Mapping on GPU.

Stochastic Heuristic Optimization (code for IA-308 lecture on metaheuristics).

Stochastic Heuristic Optimization (code for IA-308 lecture on metaheuristics).

Repository laravel pour l'ENSTA Paris

Stochastic Heuristic Optimization (code for IA-308 lecture on metaheuristics).

Stochastic Heuristic Optimization (code for IA-308 lecture on metaheuristics).

Stochastic Heuristic Optimization (code for IA-308 lecture on metaheuristics).