Gianni Lunardi

Gianni Lunardi

Auto-generated profile, based on publicly available information

Gianni Lunardi

Field Robotics Laboratory South Tyrol, Free University of Bozen-Bolzano, Bozen-Bolzano, Italy

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
19 December 2023 in IEEE Access
Verified
Journal Article
Open access
GLGianni Lunardi
Gianni Lunardi
TCThomas Corbères
Thomas Corbères
CMCarlos Mastalli
Carlos Mastalli
NMNicolas Mansard
Nicolas Mansard
TFThomas Flayols
Thomas Flayols
APAndrea Del Prete
Andrea Del Prete
Full-dynamics model predictive control (MPC) has recently been applied to quadrupedal locomotion in semi-unstructured environments. These advances have been fueled by the availability of efficient trajectory optimization (TO) algorithms and inexpensive computational power. The main advantages of full-dynamics MPC are (i) enabling complex locomotion manoeuvres, (ii) considering actuation limits, and (iii) improving robot stability. However, to make the TO problem sufficiently simple to be solved at run time, reference swing foot trajectories are usually tracked in the MPC formulation. These trajectories are often computed independently of the motion of the joints, limiting the approach generality and capability. To address this limitation, we present a full-dynamics MPC formulation that does not require reference swing-foot trajectories, featuring a novel cost function targeting swing foot motion and considering environmental information. Removing the need for reference swing foot trajectories, our approach can also automatically adjust footstep locations, as long as the contact surfaces are predefined. We have validated our MPC formulation through simulations and experiments on the ANYmal B robot. Our approach has similar computational efficiency to state-of-the-art formulations, while displaying superior push-recovery capabilities on various terrains.

16 September 2026 in Science Robotics
Verified
Journal Article
Closed access
OBOliver Bimber
Oliver Bimber
KEKarl Dietrich von Ellenrieder
Karl Dietrich von Ellenrieder
MHMichael Haller
Michael Haller
RNRakesh John Amala Arokia Nathan
Rakesh John Amala Arokia Nathan
GLGianni Lunardi
Gianni Lunardi
JNJeremy Niven
Jeremy Niven
In vegetated environments, such as forests, exploratory robots play a vital role in navigating complex, cluttered environments where human access is limited and traditional equipment struggles. Visual occlusion from obstacles, such as foliage, can severely obstruct a robot’s sensors, impairing scene understanding. We show that “peering,” a characteristic side-to-side movement used by insects to overcome their visual limitations, can also allow robots to markedly improve visual reasoning under partial occlusion. This is accomplished by applying core signal processing principles, specifically optical synthetic aperture sensing, together with the vision reasoning capabilities of modern large multimodal models. Peering enables real-time, high-resolution, and wavelength-independent perception, which is crucial for vision-based scene understanding across a wide range of applications. The approach is low cost and immediately deployable on any camera-equipped robot. We investigated different peering motions and occlusion masking strategies, demonstrating that, unlike peering, state-of-the-art multiview three-dimensional vision techniques fail under these conditions because of their high susceptibility to occlusion. Our experiments were carried out on an industrial-grade quadrupedal robot. However, the ability to peer is not limited to such platforms but potentially also applicable to bipedal, hexapod, wheeled, or crawling platforms. Robots that can effectively see through partial occlusion will gain superior perception abilities, including enhanced scene understanding, situational awareness, camouflage breaking, and advanced navigation in complex environments.