Swarm-SLAM: Collaborative Simultaneous Localization and Mapping [paper] [code] [video]

Decentralized Collaborative Simultaneous Localization and Mapping Framework for Multi-Robot Systems.
An open-source C-SLAM system designed to be scalable, flexible, decentralized, and sparse, which are all key properties in swarm robotics. Our system supports lidar, stereo, and RGB-D sensing, and it includes a novel inter-robot loop closure prioritization technique that reduces inter-robot communication and accelerates the convergence.

Improving Place Recognition via Robust Pose Graph Optimization [paper] [code]

Self-Supervised Domain Calibration and Uncertainty Estimation for Place Recognition.
We propose a self-supervised domain calibration procedure based on robust pose graph optimization from Simultaneous Localization and Mapping (SLAM) as the supervision signal without requiring GPS or manual labeling. Moreover, we leverage the procedure to improve uncertainty estimation for place recognition matches which is important in safety critical applications.

Human State Estimation for IoT, Robotics, and Augmented Reality [paper0] [paper1]

Human state estimation with consumer-grade devices.
We propose novel approaches to human state estimation to infer the position of pedestrians in device-based, and device-free settings. Work done during a research internship at the Samsung AI Center Montreal.

Debugging and Performance Analysis for Robot Operating System (ROS) 2 [paper0] [paper1]

Message flow analysis with complex causal links for distributed ROS 2 systems.
We introduce novel open-source tracing tools and techniques for ROS 2 to identify delays, bottlenecks and critical paths inside centralized, or distributed systems.

Collaborative (Multi-Robot) SLAM Survey [paper]

Towards Collaborative Simultaneous Localization and Mapping: a Survey of the Current Research Landscape.
In this survey, we introduce the basic concepts of C-SLAM and present a thorough literature review. We also outline the major challenges and limitations of C-SLAM in terms of robustness, communication, and resource management. We conclude by exploring the area's current trends and promising research avenues.

DOOR-SLAM: Distributed SLAM with Outlier Rejection [paper] [code] [video]

Distributed, Online, and Outlier Resilient SLAM for Robotic Teams.
A fully distributed SLAM system with an outlier rejection mechanism that can work with less conservative parameters. DOOR-SLAM is based on peer-to-peer communication and does not require full connectivity among the robots. It includes two key modules: a pose graph optimizer combined with a distributed pairwise consistent measurement set maximization algorithm to reject spurious inter-robot loop closures; and a distributed SLAM front-end that detects inter-robot loop closures without exchanging raw sensor data.

Outlier Rejection in SLAM [paper]

Modeling Perceptual Aliasing in SLAM via Discrete-Continuous Graphical Models.
This paper provides a unified framework to model perceptual aliasing in SLAM and provides practical algorithms that can cope with outliers without relying on any initial guess. We present two main contributions. The first is a discrete-continuous graphical model (DC-GM) for SLAM: The continuous portion of the DC-GM captures the standard SLAM problem, while the discrete portion describes the selection of the outliers and models their correlation. The second contribution is a semidefinite relaxation to perform inference in the DC-GM that returns estimates with provable sub-optimality guarantees.

Autonomous Exploration with Teams of Flying Drones [paper]

Search and Rescue with Sparsely Connected Swarms.
We propose a decentralized search system that only requires sporadic connectivity and allows information diffusion through the swarm of robots whenever possible.

Distributed Exploration with Teams of Robots in Risky Environments [paper] [code]

DORA: Distributed Online Risk-Aware Explorer.
We present Distributed Online Risk-Aware (DORA) Explorer, an exploration system that leverages decentralized information sharing to update a common risk belief map.