Відео

Most of the robotic hands are equipped with relatively simple force sensors to detect contact with manipulated objects. Very often they are only attached to the finger's tips and are not sufficient to measure the interaction forces for all shapes of objects and grasp types. The goal of this research was to develop a sensory glove that can be used on the existing robot's hands to enhance the sen...

Robots face challenges in perceiving new scenes, particularly when registering objects from a single perspective, resulting in incomplete shape information about objects. Partial object models negatively influence the performance of grasping methods. To address this, robots can scan the scene from various perspectives or employ methods to directly fill in unknown regions. This research reexamin...

Robots have limited perception capabilities when observing the scene from a single viewpoint. Some objects on the scene might be partially occluded and their 3D shape is not fully available to the robot. Existing methods obtain object models through a series of observations using RGB-D sensors or the robot is trained to operate in the presence of occlusions. In this paper, we directly address o...

creef.put.poznan.pl/artykul/samochody-autonomiczne-na-warie

Franka Emika Panda FR3 with a custom-made 3D-printed griper in the new Robotic Manipulation Laboratory (related to the NCN ProRoc project).

Our Mobot robot using Edge Insights for Autonomous Mobile Robots (EI for AMR) from Intel on ROS2: www.intel.com/content/www/us/en/developer/topic-technology/edge-5g/edge-solutions/autonomous-mobile-robots/overview.html

In this paper, we investigate the problem of state estimation of rotational articulated objects during robotic interaction. We estimate the position of a joint axis and the current rotation of an object from a pair of RGB-D images registered by the depth camera mounted on the robot. However, the camera mounted on the robot has limited view due to occlusions of the robot's arm. Moreover, some co...

A video from the paper presented at IEEE/RSJ IROS 2021 (Prague, on-line)

In this paper, we deal with the problem of full-body path planning for walking robots. The state of walking robots is defined in multi-dimensional space. Path planning requires defining the path of the feet and the robot's body. Moreover, the planner should check multiple constraints like static stability, self-collisions, collisions with the terrain, and the legs workspace. As a result, checki...

Robots have limited perception capabilities when observing a new scene. When the objects on the scene are registered from a single perspective, only partial information about the shape of the objects is registered. Incomplete models of objects influence the performance of grasping methods. In this case, the robot should scan the scene from other perspectives to collect information about the obj...

Supplemental video for the paper "Learning from Experience for Rapid Generation of Local Car Maneuvers" submitted to Engineering Applications of Artificial Intelligence. Abstract: Being able to rapidly respond to the changing scenes and traffic situations by generating feasible local paths is of pivotal importance for car autonomy. We propose to train a deep neural network (DNN) to plan feasibl...

More at: robot40.put.poznan.pl/

• SLAM for autonomous vehicles: day and night,, under dierent weather conditions. • 3-D laser scanner is the sensor of choice for automotive SLAM. • Application: ADAS for city buses that requires accurate localization in mixed outdoor/indoor environments. • Plane-LOAM includes new map representation and improved data association. • Plane-LOAM estimates the full 6 d.o.f. sensor pose and does not...

RiSA 2021 Promo video

Practical Aspects of Detection and Grasping Objects by a Mobile Manipulating Robot

Convolutional Neural Network-based Local Obstacle Avoidance for a Mobile Robot

Christmas at Mobile Robots Laboratory

Autonomous vehicles: bridging the gap between uncertainperception and provably safe actions

Rapid path planning for autonomous car - navigation in the traffic jam

Rapid path planning for autonomous car - collision avoidance

Robot 4.0 project: autonomous driving between workspaces

Robot 4.0 - localization and building Octomap

Robot 4.0 - localization and 3D perception

CNN-based Foothold Selection for Mechanically Adaptive Soft Foot

Building 3D thermal maps in real-time

Budowa mapy termicznej 3D w czasie rzeczywistym (PL)

Spatiotemporal Calibration of Camera and 3D Laser Scanner

Cross-modal transfer learning forsegmentation of non-stationary objectsusing lidar intensity data

A Fast and Practical Method of Indoor Localization for Resource-Constrained Devices [...]