Some videos of our research are reported in the following
YouTube Also visit our YouTube channel
Press, Talks and Interviews
In this section we collect our media related to press, talks and interviewsWatch videos
ERF 2021 - Canopies presented at "New Horizon projects"
Andrea Gasparri presents the H2020 project CANOPIES for the participants of the European Robotics Forum 2021
Euronews - Robot farming: Fast, cheap & better for the environment
Andrea Gasparri was interviewed by Euronews' Denis Loctier for Futuris to present the European research project PANTHEON
Euronews - Robots, drones and the future of farming
Our project PANTHEON was featured on Euronews Futuris as an example of how the new generation of robots can help farmers and agronomists make agriculture cheaper and more environmentally friendly
FIRA 2019 - Scientific Workshop organized by RobAgri (French Robotics Association)
Andrea Gasparri was invited as speaker to FIRA 2019, a scientific workshop organized by RobAgri. The workhop presentation, entitled "Project PANTHEON: Precision Farming of Hazelnut Orchard", provides an overview of the Supervisory Control And Data Acquisition (SCADA) system for the precision farming of hazelnut orchards proposed in the project PANTHEON
Corriere della sera - Robots, the challenge in Lazio for health and agriculture
Andrea Gasparri presents the sucker management system developed in Pantheon project during the national interview "Robots, the challenge in Lazio for health and agriculture" - Corriere della sera (in Italian)
Local Interview - Engineering as a snack: talking about Precision Agriculture
Andrea Gasparri talks about the Precision Agriculture paradigm and presents the projects Pantheon and Canopies during the local interview "Engineering as a snack: talking about Precision Agriculture" (in Italian)
2021 European Researchers' Night - Robotics in Precision Agriculture
Martina Lippi talks about the role of robotics in Precision Agriculture and presents the research activities of the NEWLINE group within the projects Pantheon and Canopies for the 2021 European Researchers' Night (in Italian)
In this section we consider problems of distributed coordination which consist in designing control strategies to let teams of agents reach desired configurations or motion objectives exploiting only local informationWatch videos
A Distributed Swarm Aggregation Algorithm for Bar Shaped Multi-Robot Systems
In this work we consider a swarm of agents, which are shaped as bars with a certain orientation in the state space. Members of the swarm have to reach an aggregate state, while guaranteeing the collision avoidance and possibly achieving an angular consensus.
Adaptive Potential-Based Control Design for Multi-Agent Networks
In this work we address the problem of dynamically tuning gains for multi-agent networks under potential- based control design. We propose a distributed and adaptive gain controller that preserves a designed pairwise interaction strength, independent of the network size.
Multi-Robot Field of View Control with Adaptive Decentralization
In this work, we propose a general coordinated motion framework for multi-robot systems with triangular FOVs capable of guaranteeing stability under asymmetric (directed) interactions. By proving that asymmetry in multi-robot interactions can lead to degenerate configurations for which a fully decentralized controller may be insufficient to achieve coordination, we introduce a switching control mechanism that achieves adaptive decentralization, enabling collaborative behaviors that seek support of a centralized planner for situations that are inherently unstable.
Distributed Connectivity Maintenance in Multi-Agent Systems with Field of View Interactions
In this work we consider the problem of coordinating a multi-agent system equipped with limited field of view sensors. We propose a generic coordination control framework for directed interactions and provide one of its application to maintain connectivity while optimizing the quality of the field of views.
Dynamic Resilient Containment Control in Multi-Robot Systems
In this work we study the problem of designing a local interaction protocol that drives a set of agents towards a region delimited by the positions of another set of agents, under the presence of adversaries in the network, i.e., agents that intentionally or accidentally try to disrupt the objective of the multi-agent system.
In this section we report works that propose distributed algorithms to solve class of optimization problems exploiting only local informationWatch videos
Finite-Time Distributed Tracking for Time-Varying Quadratic Programming
In this work we address a class of time-varying quadratic optimization problems with linear time-varying inequality constraints for which we propose a finite-time distributed algorithm for a multi-agent system able to track the optimal solution obtained with the application of the Karush-Kuhn-Tucker conditions.
A Finite-time Distributed Protocol for Link Prediction in Networked Multi-Agent Systems
This work addresses the finite-time distributed link prediction problem in networked multi-agent systems which consists in estimating the likelihood of existence of neighboring links in the network, exploiting only local information. Notably, this setting extends the framework introduced by Pech et al., which considered a complete network topology and was based on centralized architecture, to the case of sparse graphs and distributed computation.
In this section we report some of our works about different aspects of precision agriculture such as navigation and SLAM problemsWatch videos
A Navigation Architecture for Ackermann Vehicles in Precision Farming
In this work we propose a full navigation stack purposely designed for the autonomous navigation of Ackermann steering vehicles in precision farming settings. The proposed stack is composed of a local planner and a pose regulation controller, both implemented in ROS.
A Hierarchical and Compact SLAM Architecture for Autonomous Vehicles in Large-Scale Orchard Farming
In this work we propose a compact and hierarchical Simultaneous Localization And Mapping system purposely designed for large-scale hazelnut orchard farming. The proposed system is composed of two layers: (i) an Extended Kalman Filter (EKF) that performs a SLAM and (ii) a Kalman Filter (KF) that estimates the planting pattern of the field.
MP-STSP: A Multi-Platform Steiner Travelling Salesman Problem Formulation for Precision Farming in Large-Scale Orchards
In this work we propose a global planning strategy to optimally move a team of robotic platforms within the orchard especially when operating in large-scale scenarios in order to perform precision farming activities on individual trees, such as targeted spraying or data collectiong for pest and disease monitoring.
Suckers Emission Detection and Volume Estimation for the Precision Farming of Hazelnut Orchards
In this work, we address the hazelnut sucker detection and canopy volume estimation problem on a per-plant basis. An end-to-end algorithm for detecting the presence of suckers and for estimating their canopy based on three major steps is proposed: i) first a sparse point cloud-based representation of the suckers is detected; ii) then an approximated canopy estimation is achieved by means of a tailored meshing strategy that performs a leaf-based clustering and an iterative clusters connection; iii) finally the volume is estimated by the resulting mesh.
Autonomous Suckers Management in Large-scale Hazelnut Orchards
In this work we propose an autonomous suckers management architecture which allows the robot to autonomously navigate the field, detect suckers, compute the needed amount of herbicide for each plant and provide it.
In this section we collect additional multimedia materialWatch videos
Firmware-Embedded Control Loop and Extended Kalman Filter for Crazyflie 2.0
In this work we consider the problem of introducing a low-level control loop and an Extended Kalman Filter (EKF) into the firmware of a Crazyflie 2.0 nano quadcopter . External position (x,y,z) measurements are provided for the EKF by our OptiTrack Motion Capture System.