ALMA

ALMA (Ageing Without Losing Mobility and Autonomy) is a European project focused on supporting the autonomous mobility, navigation, and orientation of the mobility-impaired person (elderly and/or temporarily or permanently disabled person).

The ALMA system is a modular combination of advanced hardware and software technologies into an integrated and modular cost-effective system. AIRLab contributed to ALMA with its Personal Mobility Kit.

Contact: Matteo Matteucci

For additional details: http://www.alma-aal.org/

Jedi Trainer

In Jedi Trainer a drone is flying around a Jedi knight trainee aiming at training its ability in using the light saber, as in the first episode of the Star wars saga with Luke Skywalker.

By analyzing the image from the onboard camera, the drone maintains the distance from the player, keeping it always in the image, and moving slightly left and right as to look for the best position to shot. When appropriate, it makes a sound with its propeller, simulating a laser shot, and the player has to parry it by putting the light saber in front of her/his chest.

The drone is intrinsically adapting to the style of movement of the player: a more active player will have to face a more active trainer.

Robotower

Robotower is a game where an omnidirectional robot and a human player confront in a playground 4×4 m, having four towers on the corners. Aim of the robot is to knock down the towers. Aim of the human player is to defend the towers for at least 3′ by intercepting the robot’s path. The human player can also push a button on the tower, this will lit a LED every 2.5″; when all four LEDs are lit, the human player has conquered the tower, and the robot cannot aim at it any longer. Of course, while the player pushes a button the robot may aim at another tower.

The system can estimate the the player’s skill on line and modify the capabilities of the robot to obtain an even game, in accordance to the theory of flow. There is also the possibility to trigger deceptive actions, which reinforce even more the sensation to play against a rational agent.

Presentation of the game.

Robogames

Robots playing with people in physically interactive games exploit both the abilities requited to autonomous robots (such as: mapping, perception, navigation, planning, …), but also those required to appear as effective players and good play companions, involving the players in challenging and satisfactory games, matching their ability.

We have developed many games gradually exploring different facets of the development of games hwere a player is an autonomous robot, from the perception and actuation abilities needed to play following the game rules, while guaranteeing the safety of the players, to timing in different aspects, to the characteristics of the robot (e.g., shape, speed, materials, sensors…), to involvement and adaptation to the skill of the player, either intrinsic or learned while playing.

A selection of the developed games is listed here below.

Robot and disability

Robots can be successfully applied with success with people with disabilities. Since years we are developing robots, also in collaboration wit care centers, which could be used for inclusive play . A web site dedicated to this activity is http://playbot4all.polimi.it.

Samples of these robots are also listed here below.

Concierge

Concierge is a robotic head intended to stay on the side of an office door and following with the “eyes” the persons passing in the corridor. When a person comes to the door Concierge makes a “Yes” or “No” gesture according to the possibility to disturb the person in the office. Concierge can be dressed in different ways, corresponding to different psychological types, expressing the same behavior in different flavors. The more appreciated is the funky one.

Contact person: Andrea Bonarini

https://www.youtube.com/watch?v=7TNgOSBhVMU

Benchmarks for Autonomous Robots

Benchmarking means objectively measuring the performance of a robot when executing a task. Being able to benchmark robot systems is necessary to compare their performance, and thus to better understand their strenghts and weaknesses. Both research and industry need this to progress.

However, when dealing with autonomous agents benchmarking is tricky. How to devise testing procedures that yield objective results? What metrics capture the key points of the robot performance? How can robots that perform the same complex action differently be compared?

AIRLab has been working on these issues for a long time, accumulating experience in both methodology and real-world benchmark design, setup and execution.

Over the years, we participated -and are participating- to many European projects about robot benchmarking, including RAWSEEDS​ (FP6), RoCKIn​ (FP7), RockEU2 (H2020), RobMoSys (H2020), EUROBENCH (H2020), SciRoc (H2020), METRICS (H2020).

Contact: Matteo Matteucci

i.Drive

i.Drive is an interdepartmental laboratory where AIRLab is the technology provider for robotics.

The laboratory aims at developing inter-disciplinary proficiency required for analysis and modelling of behavioral aspects due to the interaction between driver, vehicle, infrastructure, and environment through:

  • A fixed structural component based on a virtual realty simulator aimed at the ex-ante test of expected behavioral models, the joined optimization of vehicle and road infrastructure, the increase of ex-post and in-itinere statistical significance ofexperiments carried out on roads;
  • A mobile component based on an instrumented vehicle aimed at measuring on field performance and reactions of drivers in different driving conditions and at collecting environmental data to be reproduced ex-post by simulation.

Contact: Matteo Matteucci

For additional details: http://www.idrive.polimi.it/

MADROB + BEAST

MADROB (Modular Active Door for RObot Benchmarking) and BEAST (Benchmark-Enabling Active Shopping Trolley) are benchmarks for autonomous robots aimed at measuring their capabilities and performance when dealing with devices that are common in human environments.

MADROB is focused on opening doors; BEAST considers the problem of pushing a shopping trolley. Both make use of a device with the same features of its real counterpart, fitted with sensors (to assess the actions of the robots on it: e.g., force applied to the handle of the door, precision in following a trajectory with the cart) and actuators (to introduce disturbances simulating real-world phenomena: e.g., wind pushing the door panel, stone under the trolley’s wheel).

Beyond the hardware and software, MADROB and BEAST also comprise procedures and performance metrics that enable objective evaluation of the performance of robots, as well as comparisons between different robots and between a robots and humans.

Contact: Matteo Matteucci

For additional details: http://eurobench2020.eu/developing-the-framework/modular-active-door-for-robot-benchmarking-madrob/, http://eurobench2020.eu/developing-the-framework/benchmark-enabling-active-shopping-trolley-beast/

Personal Mobility Kit

The PMK is an add-on for commercial electric wheelchairs that uses robotic technology to provide two new functionalities:

  • autonomous driving, where the user only has to select her goal and the PMK drives the wheelchair safely to destination;
  • assisted driving, where the user is in charge of driving and the PMK only intervenes to ensure safety (e.g., slowing down to avoid a collision with a child jumping in front of the wheelchair) or provide help in difficult maneuvers (e.g., while approaching doorways).

The PMK has been developed with the collaboration of disabled people. Its design and implementation are focused on the principle of shared autonomy: the robotic part of the wheelchair only intervenes when this actually makes the user feel more empowered by this intervention, augmenting the user’s autonomy and independence.

Contact: Matteo Matteucci