A5067891958- Robotic Path Planning Algorithms
- Robotics and Sensor-Based Localization
- Modular Robots and Swarm Intelligence
- 3D Surveying and Cultural Heritage
- Aerospace Engineering and Energy Systems
- Robotics and Automated Systems
- Spacecraft Dynamics and Control
- Underwater Vehicles and Communication Systems
- Medical Image Segmentation Techniques
- Inertial Sensor and Navigation
- Robotic Locomotion and Control
- Remote Sensing and LiDAR Applications
- Image Retrieval and Classification Techniques
- Advanced Image and Video Retrieval Techniques
Carnegie Mellon University
2020-2024
Centro de Tecnologia da Informação Renato Archer
2020
Universidade Estadual de Campinas (UNICAMP)
2019
We propose Super Odometry, a high-precision multi-modal sensor fusion framework, providing simple but effective way to fuse multiple sensors such as LiDAR, camera, and IMU achieve robust state estimation in perceptually-degraded environments. Different from traditional sensor-fusion methods, Odometry employs an IMU-centric data processing pipeline, which combines the advantages of loosely coupled methods with tightly recovers motion coarse-to-fine manner. The proposed framework is composed...
This article surveys recent progress and discusses future opportunities for simultaneous localization mapping (SLAM) in extreme underground environments. SLAM subterranean environments, from tunnels, caves, man-made structures on Earth, to lava tubes Mars, is a key enabler range of applications, such as planetary exploration, search rescue, disaster response, automated mining, among others. environments has recently received substantial attention, thanks the <italic...
This paper reports on the state of art in underground SLAM by discussing different strategies and results across six teams that participated three-year-long SubT competition. In particular, has four main goals. First, we review algorithms, architectures, systems adopted teams; particular emphasis is put lidar-centric solutions (the go-to approach for virtually all competition), heterogeneous multi-robot operation (including both aerial ground robots), real-world (from presence obscurants to...
Subterranean robot exploration is difficult, with many mobility, communications, and navigation challenges that require an approach a diverse set of systems, reliable autonomy. While prior work has demonstrated partial successes in addressing the problem, here we convey comprehensive to address problem subterranean wide range tunnel, urban, cave environments. Our driven by themes resiliency modularity, show examples how these influence design different modules. In particular, detail our...
We propose Super Odometry, a high-precision multi-modal sensor fusion framework, providing simple but effective way to fuse multiple sensors such as LiDAR, camera, and IMU achieve robust state estimation in perceptually-degraded environments. Different from traditional sensor-fusion methods, Odometry employs an IMU-centric data processing pipeline, which combines the advantages of loosely coupled methods with tightly recovers motion coarse-to-fine manner. The proposed framework is composed...
Autonomous robot navigation in austere environments is critical to missions like “search and rescue”, yet it remains difficult achieve. The recent DARPA Subterranean Challenge (SubT) highlights prominent challenges including GPS-denied through rough terrains, rapid exploration large-scale three-dimensional (3D) space, interrobot coordination over unreliable communication. Solving these requires both mechanical resilience algorithmic intelligence. Here, we present our approach that leverages...
This work presents a comparative study between three approaches of pose and velocity estimation for an robotic airship.The first approach is composed multiples second order Low-pass filters applied to GPS IMU measured data.The consists the sensor fusion GPS, IMU, Barometer Thermometer with Extended Kalman Filter (EKF) based in kinematic equations motion six degrees freedom (6-DOF) vehicle.Finally, same 6-DOF sensors are used design Unscented (UKF) as third approach.As result, we obtain...