... The winning team, RUNSWIFT, used machine learning techniques to optimize the speed of the wal... more ... The winning team, RUNSWIFT, used machine learning techniques to optimize the speed of the walking gait (particularly useful when play-ing on different fields with different carpet and foam ... One-third of the teams developed robot skills using learning ap-proaches. ...
This work presents the design of a novel neuromusculoskeletal model (NMS) of the human lower limb... more This work presents the design of a novel neuromusculoskeletal model (NMS) of the human lower limb to estimate muscle forces and moments about the hip, knee and ankle joints. This research shows it is possible to use electromyographic (EMG) signals recorded from 16 muscles to drive 34 musculotendon actuators and constrain their operation to simultaneously satisfy the production of moments across several degrees of freedom (DOF) including: hip adduction-abduction, hip flexionextension, knee flexion-extension, ankle dorsi-plantar flexion. Past research proposed the use single-DOF NMS model to estimate muscle forces and joint moments. However, these models do not properly allow muscles to operate with respect to all the DOFs associated to the joints they span. This leads to unrealistic estimations of muscle activation patterns and force production dynamics. Our proposed model was able to generate muscle forces that properly satisfied the moments generated at hip, knee and ankle joints during a variety of dynamic motor tasks.
This paper presents a novel neuromusculoskeletal (NMS) model of the human lower limb that uses th... more This paper presents a novel neuromusculoskeletal (NMS) model of the human lower limb that uses the electromyographic (EMG) signals from 16 muscles to estimate forces generated by 34 musculotendon actuators and the resulting joint moments at the hip, knee and ankle joints during varied contractile conditions. Our proposed methodology allows overcoming limitations on force computation shown by currently available NMS models, which constrain the operation of muscles to satisfy joint moments about one single degree of freedom (DOF) only (i.e. knee flexion-extension). The design of advanced human machine interfaces can benefit from the application of our proposed multi-DOF NMS model. The better estimates of the human internal state it provides with respect to single-DOF NMS models, will allow designing more intuitive humanmachine interfaces for the simultaneous EMG-driven actuation of multiple joints in lower limb powered orthoses.
In this paper we use motion capture technology together with an electromyography (EMG) driven mus... more In this paper we use motion capture technology together with an electromyography (EMG) driven musculoskeletal model of the knee joint to predict muscle behavior during human dynamic movements. We propose a muscle model based on infinitely-stiff tendons and show this allows speeding up 250 times the computation of muscle force and the resulting joint moment calculation with no loss of accuracy with respect to the previously developed elastic tendon model. We then integrate our previously developed method for the estimation of 3D musculotendon kinematics in the proposed EMG-driven model. This new code enabled the creation of a stand-alone EMG-driven model that was implemented and run on an embedded system for applications in assistive technologies such as myoelectrically controlled prostheses and orthoses.
Abstract The availability of accurate and comprehensive models of human limbs, combining high rel... more Abstract The availability of accurate and comprehensive models of human limbs, combining high reliability and real-time operation, is required to develop seamless and intuitive human-machine interfaces. Biomechanist have developed complex models of the human ...
Azzurra Robot Team (ART) is the National Italian Team for F-2000 RoboCup league, developed within... more Azzurra Robot Team (ART) is the National Italian Team for F-2000 RoboCup league, developed within the RoboCup Italia project. ART99 is formed by six academic groups and Consorzio Padova Ricerche. ART started with RoboCup-98, and its goal is to exploit the expertise and ideas from all groups in order to build a team where players have different features (hw and sw), but retain the ability to coordinate their behaviour within the team. ART99 obtained the second place in RoboCup-99 F-2000 league, and coordination among players is, in our view, the most significant achievement of the team.
Azzurra Robot Team is the result of a joint effort of seven Italian research groups from Univ. of... more Azzurra Robot Team is the result of a joint effort of seven Italian research groups from Univ. of Brescia, Univ. of Genoa, Politecnico of Milano, Univ. of Padua, Univ. of Palermo, Univ. of Parma, Univ. of Roma "La Sapienza", and the Consorzio Padova Ricerche which has provided resources and a set up of the soccer field in its Center in Padua. Our goal at Robocup 1998 has been to provide a exible and low-cost experimental team to make experience before undertaking a larger project. Our long term goal is to foster the development of research and education projects on autonomous mobile robots by exploiting the RoboCup challenge.
Motion blur is a severe problem in images grabbed by legged robots and, in particular, by small h... more Motion blur is a severe problem in images grabbed by legged robots and, in particular, by small humanoid robots. Standard feature extraction and tracking approaches typically fail when applied to sequences of images strongly affected by motion blur. In this paper, we propose a new feature detection and tracking scheme that is robust even to nonuniform motion blur. Furthermore, we developed a framework for visual odometry based on features extracted out of and matched in monocular image sequences. To reliably extract and track the features, we estimate the point spread function (PSF) of the motion blur individually for image patches obtained via a clustering technique and only consider highly distinctive features during matching. We present experiments performed on standard datasets corrupted with motion blur and on images taken by a camera mounted on walking small humanoid robots to show the effectiveness of our approach. The experiments demonstrate that our technique is able to reliably extract and match features and that it is furthermore able to generate a correct visual odometry, even in presence of strong motion blur effects and without the aid of any inertial measurement sensor.
The localization problem for an autonomous robot moving in a known environment is a well studied ... more The localization problem for an autonomous robot moving in a known environment is a well studied problem which has seen many elegant solutions. Robot localization in a dynamic environment populated by several moving obstacles, however, is still a challenge for research. In this paper, we use an omnidirectional camera mounted on a mobile robot to perform a sort of scan matching. The omnidirectional vision system finds the distances of the closest color transitions in the environment, mimicking the way laser rangefinders detect the closest obstacles. The similarity of our sensor with classical rangefinders allows the use of practically unmodified Monte Carlo algorithms, with the additional advantage of being able to easily detect occlusions caused by moving obstacles. The proposed system was initially implemented in the RoboCup Middle-Size domain, but the experiments we present in this paper prove it to be valid in a general indoor environment with natural color transitions. We present localization experiments both in the RoboCup environment and in an unmodified office environment. In addition, we assessed the robustness of the system to sensor occlusions caused by other moving robots. The localization system runs in real-time on low-cost hardware.
Planning multiple autonomous robots motion in space and time
We address the problem of planning the motion of multiple autonomous robots, by analysing their b... more We address the problem of planning the motion of multiple autonomous robots, by analysing their behaviour in space and time. Proper representations have been studied for both domains, with a particular emphasis on the definition of some performance indexes to weight the goodness of a path concerning motion and time performances. Sublinear algorithms have been used for planning in space while reasoning in the temporal domain is based on a proper subdivision of the time axis that leads to polynomial algorithms
IEEE Transactions on Robotics and Automation, 2002
As research progresses in distributed robotic systems, more and more aspects of multi-robot syste... more As research progresses in distributed robotic systems, more and more aspects of multi-robot systems are being explored. This special issue on Multi-Robot Systems provides a broad sampling of the research that is currently ongoing in the field of distributed mobile robot systems. To help categorize this research, we have identified seven primary research topics within multi-robot systems -biological inspirations, communication, architectures, localization/mapping/exploration, object transport and manipulation, motion coordination, and reconfigurable robots. This editorial examines these research areas and discusses the special issue articles in this context. We conclude by identifying several additional open research issues in distributed mobile robotic systems.
In this paper, we present a new approach for omnidirectional vision-based self-localization in th... more In this paper, we present a new approach for omnidirectional vision-based self-localization in the RoboCup Middle-Size League. The omnidirectional vision sensor is used as a range finder (like a laser or a sonar) sensitive to colors transitions instead of nearest obstacles. This makes it possible to have a more reach information about the environment, because it is possible to discriminate between different objects painted in different colors. We implemented a Monte-Carlo localization system slightly adapted to this new type of range sensor. The system runs in real time on a low-cost pc. Experiments demonstrated the robustness of the approach. Event if the system was implemented and tested in the RoboCup Middle-Size field, the system could be used in other environments.
Collaborative Emergent Actions between Real Soccer Robots
We discuss how to induce a set of collaborative emergent actions between two soccer robots. Coope... more We discuss how to induce a set of collaborative emergent actions between two soccer robots. Cooperative abilities, like exchanging a ball, can be achieved through the use of efficient collision avoidance algorithms implemented on two players able to frequently swap their roles. These algorithms have been tested on Bart and Homer, designed at IAS Lab. of Padua Univ., that played quarter, semifinals, and finals with ART at RoboCup'99. The interaction with the ball was made easy by a directional kicker which allowed to hit the ball both frontally and laterally.
Uploads
Papers by enrico pagello