Antonello Scaldaferri

Antonello Scaldaferri


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 May 2025 in IEEE Open Journal of the Industrial Electronics Society
Verified
Journal Article
Open access
ASAntonello Scaldaferri
Antonello Scaldaferri
STSimone Tolomei
Simone Tolomei
FIFrancesco Iotti
Francesco Iotti
PGPaolo Gambino
Paolo Gambino
MPMichele Pierallini
Michele Pierallini
MGManolo Garabini
Manolo Garabini
This paper presents the mechanical design of Otto, a lightweight 8-degrees-of-freedom (8-DoF) quadrupedal robot employing Series Elastic Actuators (SEA), and a training framework for learning locomotion control policies in simulation using Reinforcement Learning (RL). Otto's design differs from typical 12-DoF quadrupeds by lacking hip adduction-abduction degrees of freedom. This reduces the robot's cost and weight and increases complexity for tasks involving base rotation and angular twist following. The elastic elements at the joints improve compliance, energy efficiency, safety, and stability, increase robustness, and reduce damage to robot hardware components. Our locomotion control approach leverages RL to optimize policies in simulation, allowing stable and efficient movement despite mechanical constraints, i.e., an 8-DoF quadrupedal robot. Through extensive simulation training, leveraging highly parallel GPU-accelerated robotic simulators, we ensure the policy is well-suited for deployment in real-world scenarios, where accurate motion control is critical for performance. The trained policy is then transferred to the physical robot platform. We demonstrate its effectiveness in various tasks and real-life scenarios with varying payloads and terrains, and compare it with a state-of-the-art model-based method. The results show that Otto, equipped with our RL-based locomotion control, achieves robust performance, compensating for the reality gap and managing the reduced DoF available in Otto.

24 July 2024 in Robotics
Verified
Journal Article
Open access
PDF file
ASAntonello Scaldaferri
Antonello Scaldaferri
FAFranco Angelini
Franco Angelini
MGManolo Garabini
Manolo Garabini
In recent years, tasks regarding autonomous mobility favoredthe use of legged robots rather than wheeled ones thanks to their higher mobility on rough and uneven terrains. This comes at the cost of more complex motion planners and controllers to ensure robot stability and balance. However, in the case of quadrupedal robots, balancing is simpler than it is for bipeds thanks to their larger support polygons. Until a few years ago, most scientists and engineers addressed the quadrupedal locomotion problem with model-based approaches, which require a great deal of modeling expertise. A new trend is the use of data-driven methods, which seem to be quite promising and have shown great results. These methods do not require any modeling effort, but they suffer from computational limitations dictated by the hardware resources used. However, only the design phase of these algorithms requires large computing resources (controller training); their execution in the operational phase (deployment), takes place in real time on common processors. Moreover, adaptive feet capable of sensing terrain profile information have been designed and have shown great performance. Still, no dynamic locomotion control method has been specifically designed to leverage the advantages and supplementary information provided by this type of adaptive feet. In this work, we investigate the use and evaluate the performance of different end-to-end control policies trained via reinforcement learning algorithms specifically designed and trained to work on quadrupedal robots equipped with passive adaptive feet for their dynamic locomotion control over a diverse set of terrains. We examine how the addition of the haptic perception of the terrain affects the locomotion performance.

8 June 2021 in arXiv
Verified
Preprint
Open access
PDF file
MFMiguel Fernandes
Miguel Fernandes
ASAntonello Scaldaferri
Antonello Scaldaferri
Giuseppe FiameniGiuseppe Fiameni
Giuseppe Fiameni
TTTao Teng
Tao Teng
MGMatteo Gatti
Matteo Gatti
Fei ChenFei Chen
Fei Chen
Grapevine winter pruning is a complex task, that requires skilled workers to execute it correctly. The complexity of this task is also the reason why it is time consuming. Considering that this operation takes about 80-120 hours/ha to be completed, and therefore is even more crucial in large-size vineyards, an automated system can help to speed up the process. To this end, this paper presents a novel multidisciplinary approach that tackles this challenging task by performing object segmentation on grapevine images, used to create a representative model of the grapevine plants. Second, a set of potential pruning points is generated from this plant representation. We will describe (a) a methodology for data acquisition and annotation, (b) a neural network fine-tuning for grapevine segmentation, (c) an image processing based method for creating the representative model of grapevines, starting from the inferred segmentation and (d) potential pruning points detection and localization, based on the plant model which is a simplification of the grapevine structure. With this approach, we are able to identify a significant set of potential pruning points on the canes, that can be used, with further selection, to derive the final set of the real pruning points.