Paolo Bevilacqua

Paolo Bevilacqua

Auto-generated profile, based on publicly available information

Paolo Bevilacqua

Department of Information Engineering and Computer Science, University of Trento, Trento, Italy

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
23 January 2018 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
PBPaolo Bevilacqua
Paolo Bevilacqua
MFMarco Frego
Marco Frego
DFDaniele Fontanelli
Daniele Fontanelli
LPLuigi Palopoli
Luigi Palopoli
We consider a vehicle consisting of a robotic walking assistant pushed by a user. The robot can guide the person along a path and suggest a velocity by various means. The vehicle moves in a crowded environment and can detect other pedestrians in the surroundings. We propose a reactive planner that modifies the path in order to avoid pedestrians in the surroundings. The algorithm relies on a very accurate model to predict the motion of each pedestrian, i.e., the headed social force model. The possible trajectories for both the vehicle and the pedestrians are modeled as clothoid curves, which are efficient to manage from the numeric point of view and are very comfortable to follow for the user. Probabilistic techniques are used to account for the variability of the motion of each pedestrian. The path is efficient to generate, is collision free (up to a certain probability), and is comfortable to follow. Simulations and comparisons with a state-of-the-art planner using real data as well as experiments are reported to prove the effectiveness of the method.

13 October 2016
Verified
Conference Paper
Closed access
PBPaolo Bevilacqua
Paolo Bevilacqua
MFMarco Frego
Marco Frego
EBEnrico Bertolazzi
Enrico Bertolazzi
DFDaniele Fontanelli
Daniele Fontanelli
LPLuigi Palopoli
Luigi Palopoli
FBFrancesco Biral
Francesco Biral
Motion planning for service robots used for human assistance in complex environments is a challenging task with multifaceted requirements. On the one hand, the generated path has to avoid obstacles and satisfy the user requirements. On the other, the generated path has to be perceived as comfortable by the user. An efficient solution to this difficult problem is based on a separation of concerns between two subproblems: 1. generating a sequence of waypoints that connects the source to the destination, 2. generating a path that joins the waypoints and complies with the dynamic constraints. In this paper, we concentrate on the second problem with an explicit focus on how to account for users' comfort. The result is accomplished by solving an optimal control problem that inherently generates the smooth trajectories required by the user. The cost functions used in the optimisation problem allows to take different dimensions of the user's comfort into consideration. Our technique lends itself to an efficient numeric solution and can be easily applied to different algorithms for waypoint generation.

24 December 2021 in IEEE Access
Verified
Journal Article
Open access
AAAlessandro Antonucci
Alessandro Antonucci
Gastone Pietro Rosati PapiniGastone Pietro Rosati Papini
Gastone Pietro Rosati Papini
PBPaolo Bevilacqua
Paolo Bevilacqua
LPLuigi Palopoli
Luigi Palopoli
DFDaniele Fontanelli
Daniele Fontanelli
Generating accurate and efficient predictions for the motion of the humans present in the scene is key to the development of effective motion planning algorithms for robots moving in promiscuous areas, where wrong planning decisions could generate safety hazard or simply make the presence of the robot “socially” unacceptable. Our approach to predict human motion is based on a neural network of a peculiar kind. Contrary to conventional deep neural networks, our network embeds in its structure the popular Social Force Model, a dynamic equation describing the motion in physical terms. This choice allows us to concentrate the learning phase in the aspects which are really unknown (i.e., the model’s parameters) and to keep the structure of the network simple and manageable. As a result, we are able to obtain a good prediction accuracy even by using a small and synthetically generated training set. Importantly, the prediction accuracy remains acceptable even when the network is applied in scenarios radically different from those for which it was trained. Finally, the choices of the network are “explainable”, as they can be interpreted in physical terms. Comparative and experimental results prove the effectiveness of the proposed approach.

1 March 2022 in Robotics and Autonomous Systems
Verified
Journal Article
Closed access
MBManuel Boldrer
Manuel Boldrer
AAAlessandro Antonucci
Alessandro Antonucci
PBPaolo Bevilacqua
Paolo Bevilacqua
LPLuigi Palopoli
Luigi Palopoli
DFDaniele Fontanelli
Daniele Fontanelli

1 December 2016
Verified
Conference Paper
Closed access
MFMarco Frego
Marco Frego
PBPaolo Bevilacqua
Paolo Bevilacqua
EBEnrico Bertolazzi
Enrico Bertolazzi
FBFrancesco Biral
Francesco Biral
DFDaniele Fontanelli
Daniele Fontanelli
LPLuigi Palopoli
Luigi Palopoli
We consider the problem of trajectory planning with geometric constraints for a car-like vehicle. The vehicle is described by its dynamic model, considering such effects as lateral slipping and aerodynamic drag. We propose a modular solution, where three different problems are identified and solved by specific modules. The execution of the three modules can be orchestrated in different ways in order to produce efficient solutions to a variety of trajectory planning problems (e.g., obstacle avoidance, or overtake). As a specific example, we show how to generate the optimal lap on a specified racing track. The numeric examples provided in the paper are good witnesses of the effectiveness of our strategy.

7 July 2020 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
MFMarco Frego
Marco Frego
PBPaolo Bevilacqua
Paolo Bevilacqua
SDStefano Divan
Stefano Divan
FZFabiano Zenatti
Fabiano Zenatti
LPLuigi Palopoli
Luigi Palopoli
DFDaniele Fontanelli
Daniele Fontanelli
A combined minimum time - minimum jerk traffic management system for the vehicle coordination in an automated warehouse is presented. The algorithm is organised in two steps: in the first, a simple minimum time optimisation problem is solved, in the second step, this time-optimal solution is refined into a smooth minimum jerk plan for the autonomous forklifts in order to avoid impulsive forces that may unbalance the vehicle. For the first step, we propose a novel approach based on Linear Programming, which guarantees convergence to the optimal solution starting from a feasible point, and a low computational overhead, which makes it suitable for real-time applications. The output of this step is a piecewise constant velocity profile for all the moving robots that ensures collision avoidance. The second step takes such speed profile and generates its smoothed version, which minimises the jerk while respecting the same levels of safety of the solution generated by the first step. We discuss the different solutions with simulation and experimental data.