Giovanni Beltrame

Doctorat - Polytechnique

Co-superviseur⋅e :

Collaborateur·rice de recherche - Polytechnique Montreal

Co-superviseur⋅e :

Maîtrise recherche - Polytechnique

Co-superviseur⋅e :

Doctorat - Polytechnique

Co-superviseur⋅e :

Jana Pavlasek

Github

Simon Roy

Maîtrise recherche - UdeM

Co-superviseur⋅e :

Jana Pavlasek

Site web

Github

Soma Soma

Doctorat - Polytechnique

Co-superviseur⋅e :

Jana Pavlasek

Publications

Neural Incremental Dynamic Inversion Control of a Multirotor Robotic Airship

Ely Carneiro de Paiva

José Raul Azinheira

Rafael de Angelis Cordeiro

José Reginaldo H. Carvalho

Apolo Marton

2024-12-31

International Journal of Intelligent Systems (publié)

PEACE: Prompt Engineering Automation for CLIPSeg Enhancement for Safe-Landing Zone Segmentation

Rongge Zhang

Antoine Robillard

Safe landing is essential in robotics applications, from industrial settings to space exploration. As artificial intelligence advances, we h… (voir plus)ave developed PEACE (Prompt Engineering Automation for CLIPSeg Enhancement), a system that automatically generates and refines prompts for identifying landing zones in changing environments. Traditional approaches using fixed prompts for open-vocabulary models struggle with environmental changes and can lead to dangerous outcomes when conditions are not represented in the predefined prompts. PEACE addresses this limitation by dynamically adapting to shifting data distributions. Our key innovation is the dual segmentation of safe and unsafe landing zones, allowing the system to refine the results by removing unsafe areas from potential landing sites. Using only monocular cameras and image segmentation, PEACE can safely guide descent operations from 100 meters to altitudes as low as 20 meters. The testing shows that PEACE significantly outperforms the standard CLIP and CLIPSeg prompting methods, improving the successful identification of safe landing zones from 57% to 92%. We have also demonstrated enhanced performance when replacing CLIPSeg with FastSAM. The complete source code is available as an open-source software 1.

2024-12-31

IROS (publié)

BlabberSeg: Real-Time Embedded Open-Vocabulary Aerial Segmentation

Ricardo de Azambuja

Real-time aerial image segmentation plays an important role in the environmental perception of Uncrewed Aerial Vehicles (UAVs). We introduce… (voir plus) BlabberSeg, an optimized Vision-Language Model built on CLIPSeg for on-board, real-time processing of aerial images by UAVs. BlabberSeg improves the efficiency of CLIPSeg by reusing prompt and model features, reducing computational overhead while achieving real-time open-vocabulary aerial segmentation. We validated BlabberSeg in a safe landing scenario using the Dynamic Open-Vocabulary Enhanced SafE-Landing with Intelligence (DOVESEI) framework, which uses visual servoing and open-vocabulary segmentation. BlabberSeg reduces computational costs significantly, with a speed increase of 927.41% (16.78 Hz) on a NVIDIA Jetson Orin AGX (64GB) compared with the original CLIPSeg (1.81Hz), achieving real-time aerial segmentation with negligible loss in accuracy (2.1% as the ratio of the correctly segmented area with respect to CLIPSeg). BlabberSeg's source code is open and available online.

2024-10-15

ArXiv (prépublication)

Active Semantic Mapping and Pose Graph Spectral Analysis for Robot Exploration

Rongge Zhang

2024-10-13

2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (publié)

Physical Simulation for Multi-agent Multi-machine Tending

Abdalwhab Abdalwhab

David St-Onge

2024-10-10

ArXiv (prépublication)

Beyond the lab: Feasibility of cognitive neuroscience data collection during a speleological expedition

Anita Paas

Hugo R. Jourde

Arnaud Brignol

Marie-Anick Savard

Zseyvfin Eyqvelle

Samuel Bassetto

Emily B.J. Coffey

2024-10-04

Journal of Environmental Psychology (publié)

Multi-Objective Risk Assessment Framework for Exploration Planning Using Terrain and Traversability Analysis

Riana Gagnon Souleiman

Vivek Shankar Vardharajan

2024-10-03

ArXiv (prépublication)

Frequency-based View Selection in Gaussian Splatting Reconstruction

Monica Li

Pierre-Yves Lajoie

Three-dimensional reconstruction is a fundamental problem in robotics perception. We examine the problem of active view selection to perform… (voir plus) 3D Gaussian Splatting reconstructions with as few input images as possible. Although 3D Gaussian Splatting has made significant progress in image rendering and 3D reconstruction, the quality of the reconstruction is strongly impacted by the selection of 2D images and the estimation of camera poses through Structure-from-Motion (SfM) algorithms. Current methods to select views that rely on uncertainties from occlusions, depth ambiguities, or neural network predictions directly are insufficient to handle the issue and struggle to generalize to new scenes. By ranking the potential views in the frequency domain, we are able to effectively estimate the potential information gain of new viewpoints without ground truth data. By overcoming current constraints on model architecture and efficacy, our method achieves state-of-the-art results in view selection, demonstrating its potential for efficient image-based 3D reconstruction.

2024-09-23

ArXiv (prépublication)

Swarming Out of the Lab: Comparing Relative Localization Methods for Collective Behavior

Rafael Gomes Braga

Vivek Shankar Vardharajan

David St-Onge

2024-09-14

Lecture Notes in Computer Science (publié)

Concurrent product layout design optimization and dependency management using a modified NSGA-III approach

Yann-Seing Law-Kam Cio

Aurelian Vadean

Abolfazl Mohebbi

Sofiane Achiche

The complexity of mechatronic systems has increased with the significant advancements of technology in their components which makes their de… (voir plus)sign more challenging. This is due to the need for incorporating expertise from different domains as well as the increased number and complexity of components integrated into the product. To alleviate the burden of designing such products, many industries and researchers are attracted to the concept of modularization which is to identify a subset of system components that can form a module. To achieve this, a novel product-related dependency management approach is proposed in this paper with the support of an augmented design structure matrix. This approach makes it possible to model positive and negative dependencies and to compute the combination potency between components to form modules. This approach is then integrated into a modified non-dominated sorting genetic algorithm III to concurrently optimize the design and identify the modules. The methodology is exemplified through the case study of a layout design of an automatic greenhouse. By applying the proposed methodology to the case study, it was possible to generate concepts that decreased the number of modules from 9 down to 4 while ensuring the optimization of the design performance.

2024-08-20

Frontiers in Mechanical Engineering (publié)

LiDAR-based Real-Time Object Detection and Tracking in Dynamic Environments

Wenqiang Du

In dynamic environments, the ability to detect and track moving objects in real-time is crucial for autonomous robots to navigate safely and… (voir plus) effectively. Traditional methods for dynamic object detection rely on high accuracy odometry and maps to detect and track moving objects. However, these methods are not suitable for long-term operation in dynamic environments where the surrounding environment is constantly changing. In order to solve this problem, we propose a novel system for detecting and tracking dynamic objects in real-time using only LiDAR data. By emphasizing the extraction of low-frequency components from LiDAR data as feature points for foreground objects, our method significantly reduces the time required for object clustering and movement analysis. Additionally, we have developed a tracking approach that employs intensity-based ego-motion estimation along with a sliding window technique to assess object movements. This enables the precise identification of moving objects and enhances the system's resilience to odometry drift. Our experiments show that this system can detect and track dynamic objects in real-time with an average detection accuracy of 88.7\% and a recall rate of 89.1\%. Furthermore, our system demonstrates resilience against the prolonged drift typically associated with front-end only LiDAR odometry. All of the source code, labeled dataset, and the annotation tool are available at: https://github.com/MISTLab/lidar_dynamic_objects_detection.git

2024-07-03

ArXiv (prépublication)

Overcoming Boundaries: Interdisciplinary Challenges and Opportunities in Cognitive Neuroscience

Arnaud Brignol

Anita Paas

Luis Sotelo-Castro

David St-Onge

Emily B.J. Coffey

2024-06-30

Neuropsychologia (publié)