Videos

EMA Software Suite - production and Material Flow Planning & Work Place and Process Design (IMK)

The EMA Software Suite contains the solutions ema Plant Designer for holistic an integrated production and material flow planning and the ema Work Designer for work lace and process design.

Humanoid Whole-Body Movement Optimization from Retargeted Human Motions (INRIA)

Motion retargeting and teleoperation are powerful tools to demonstrate complex whole-body movements to humanoid robots: in a sense, they are the equivalent of kinesthetic teaching for manipulators.

Learning Task Priorities and Gains for Control of Humanoid Robots via Motion Retargeting (INRIA)

Generating complex movements in redundant robots like humanoids is classically done by means of multi-task whole-body controllers based on quadratic programming, where a multitude of tasks to optimize is organized according to strict or soft priorities.

Real-time Whole-body Motion Retargeting for Simultaneous Walking and Upper-body Movements (INRIA)

Retargeting complex whole-body motions onto humanoid robots is still an open issue. The classical motion retargeting approaches are not applicable to the robot body parts which are the most involved in a dynamic movement, e.g. legs and feet, particularly when footsteps and contact transitions are involved.

Estimation of human kinematics while running (IIT)

Development of motion tracking algorithms for time-critical applications, through an infrastructure for solving dynamically the inverse kinematics of highly articulate systems such as humans. We present a method based on the integration of differential kinematics using distance measurement on SO(3) for which the convergence is proved using Lyapunov analysis.

Human muscular fatigue during walking with IIT shoes and insoles (IIT)

Demonstration of our software infrastructure to perform real-time human motion tracking and real-time human articular stress tracking using sensorized shoes that contain force-torque sensors.

Online Human Kinematics and Dynamics Estimation with FTShoes and Skin Insoles (IIT)

Demonstration of our software infrastructure to perform real-time human motion tracking and real-time human articular stress tracking using sensorized shoes that contain force-torque sensors and capicitive skin soles.

Prediction of Human Whole-Body Movements with AE-ProMPs (INRIA)

The ability to predict the future intended movement is crucial for collaborative robots to anticipate the human actions and for assistive technologies to alert if a particular movement is non-ergonomic and potentially dangerous for the human health. We address the problem of predicting the future human whole-body movements given early observations.

Robust Real-time Whole-Body Motion Retargeting from Human to Humanoid - fast and challenging motions (INRIA)

Transferring the motion from a human operator to a humanoid robot is a crucial step to enable robots to learn from and replicate human movements. The ability to retarget in real-time whole-body motions that are challenging for the humanoid balance is critical to enable human to humanoid teleoperation.

Generating Assistive Humanoid Motions with a Multi-Robot QP Controller (INRIA)

Human-humanoid collaborative tasks require that the robot take into account the goals of the task, interaction forces with the human, and its own balance. We present a formulation for a real-time humanoid controller which allows the robot to keep itself stable, while also assisting the human in achieving their shared objectives.

Learning Robust Task Priorities and Gains for Control of Redundant Robots (INRIA)

Generating complex movements in redundant robots like humanoids is usually done by means of multi-task controllers based on quadratic programming, where a multitude of tasks is organized according to strict or soft priorities. Time-consuming tuning and expertise are required to choose suitable task priorities, and to optimize their gains.

Activity Recognition for Ergonomic Assessment of Industrial Tasks with Automatic Feature Selection (INRIA)

In industry, ergonomic assessment is currently performed manually based on the identification of postures and actions by experts. We aim at proposing a system for automatic ergonomic assessment based on activity recognition. We define a taxonomy of activities, composed of four levels, compatible with items evaluated in standard ergonomic worksheets.

Outdoor Motion Capture and Musculoskeletal Simulations (AnyBody)

To date, musculoskeletal simulation studies require concurrent optical motion capture and force plate data to fully analyze the biomechanics. In this joint AnyBody Technology & Xsens webinar, we present a new workflow for obtaining full force data as well as compute muscle forces, without force plates or optical motion capture.

Assistive Devices: Simulating Physiological Performance (AnyBody)

In this AnyBody webcast, we will showcase real-world examples where musculoskeletal simulations facilitated the design and evaluation of assistive devices for a number of motion scenarios. We will demonstrate how various physiological performance metrics enable engineers to create devices that achieve multiple design objectives.

iCub teleoperated walking and manipulation (IIT)

This video shows the latest results achieved by the Dynamic Interaction Control Lab at the Italian Institute of Technology on teleoperated walking and manipulation for humanoid robots. We have integrated the iCub walking algorithms with a new teleoperation system, thus allowing a human being to teleoperate the robot during locomotion and manipulation tasks.

CoDyCo 4th year demo standing up (IIT)

The video shows the real-time human inverse dynamics. Joint torques computations are obtained with a sensor fusion algorithm. Available sensors are: whole-body distributed accelerometers (robot and human), whole-body distributed force torques sensors (robot) and force plates at the feet (human).

CoDyCo 4th year demo - preliminary result (IIT)