Upload
others
View
1
Download
1
Embed Size (px)
Citation preview
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
Force and Visual Control forSafe Human−Robot Interaction
Bruno SICILIANO
www.prisma.unina.it
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
PRISMA Team
Bruno Siciliano • Luigi Villani • Vincenzo LippielloAlberto Finzi • Silvia Rossi • Franco Cutugno
Fanny Ficuciello • Fabio Ruggiero • Agostino De SantisRafik Mebarki • Antoine Petit • Jun Nishiyama • Alejandro Donaire • Aykut Satıcı
Francesca Cordella • Mariacarla Staffa • Daniela D'AuriaLuca Buonocore • Jonathan Cacace • Diana Serra • Mahdi Momeni • Andrea Fontanelli
Valeria Federico • Jonathan van der Meer
Force and Visual Control for Safe Human−Robot Interaction 2/35
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
Our Research Portfolio
Aerial RoboticsAssistive RoboticsCognitive Control of Robotic SystemsDual-Arm/Hand ManipulationForce ControlHuman−Robot InteractionInspection RoboticsLightweight Flexible ArmsMobile Dynamic Non-prehensile ManipulationMotion Generation and Biomechanical Analysis
for Human FiguresRedundant ManipulatorsRobotic Surgery TechnologySensory-Motor Synergies of Anthropomorphic
HandsService RoboticsVisual Servoing
Fund
ing
of 8.
5 M€
Force and Visual Control for Safe Human−Robot Interaction 3/35
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
Physical human-robot interaction Force control
Impedance control Force control
Visual control Position-based visual servoing Pose estimation using vision
Interaction control using vision and force Position-based visual impedance control Pose estimation using vision and force
Experiments
OutlineForce and Visual Control for Safe Human−Robot Interaction 4/35
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
Human−Robot InteractionForce and Visual Control for Safe Human−Robot Interaction 5/35
Traditional industrial robotics Segmented workspace for machines and humans
Intelligent machines working in contact with humans Haptic interfaces and teleoperators Cooperative material handling Power extenders Rehabilitation and physical training Entertainment
Human–robot interaction (HRI) Cognitive issues [cHRI]: perception, awareness, mental models Physical issues [pHRI]: safety, dependability Ethical issues: motivations and critics about HRI, acceptability
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
Physical Human−Robot InteractionForce and Visual Control for Safe Human−Robot Interaction 6/35
Risks for robots interacting with humans Heavy moving parts and objects transported Sensory data reliability Level of autonomy/unpredictable behaviours
Solutions for collaborative human–robot operation Design of non-conventional actuators (passive safety) Interaction control (active safety) Dependable algorithms for supervision and planning Fault tolerance Need for quantitative metrics
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
Force ControlForce and Visual Control for Safe Human−Robot Interaction 7/35
Motion control vs. force control Advanced industrial robotics and service robotics demand for control of interaction
between robot manipulator and humans Use of purely motion control strategy is candidate to fail (task planning accuracy) Control of contact force (compliant behaviour) Use of force/torque sensor (interfaced with robot control unit)
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
TaxonomyForce and Visual Control for Safe Human−Robot Interaction 8/35
Indirect vs. direct force control Indirect force control: force control via motion control (w/out explicit closure of force
feedback loop) Direct force control: force controlled to desired value (w/ closure of force feedback
loop)
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
Indirect Force ControlForce and Visual Control for Safe Human−Robot Interaction 9/35
Impedance control with inner motion control loop Force/torque measurements for linear and decoupled impedance Compliant frame between desired and EE frame (disturbance rejection)
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
ExperimentsForce and Visual Control for Safe Human−Robot Interaction 10/35
Set-up COMAU Smart 3-S robot Open control architecture ATI force/torque sensor 6-DOF spatial impedance
surface contact
low compliancehigh damping
high compliancelow damping
high compliancehigh damping
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
Extension to Cooperating RobotsForce and Visual Control for Safe Human−Robot Interaction 11/35
Dual-arm set-up 6ax robot 7ax robot
peg-in-hole assembly6-DOF impedance
control of absolute motionand internal forces
absolute & relative impedance absolute impedance human-object interaction
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
Service TasksForce and Visual Control for Safe Human−Robot Interaction 12/35
Set-up @ ARTS Lab, SSSA Pisa DEXTER cable-actuated robot arm
Compliance control Tasks of assisting disabled people
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
Visual ControlForce and Visual Control for Safe Human−Robot Interaction 13/35
Artificial intelligence vs. automatic control Vision capabilities bring robots nearer to human skills The information that can be extracted form images is very rich and can be used at
different levels of a hierarchical architecture
Data complexity
Highest level(Artificial Intelligence)
Visual information used to understand the world and decide
how to act
Bandwidth
Lowest level(Automatic Control)
Visual measurements usedin the control law
Visual servoing
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
TaxonomyForce and Visual Control for Safe Human−Robot Interaction 14/35
Direct visual servoing
Indirect visual servoing
Vision-basedcontrol
Robot
CameraVisual feedback≥ 100 Hz
Vision-basedcontrol
Motion control Robot
CameraVisual feedback
Joint feedback
≥ 20 Hz
≥ 100 Hz
dynamic look-and-move
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
Indirect Visual ServoingForce and Visual Control for Safe Human−Robot Interaction 15/35
3D object
Vision system
Computer
BUS
Estimated pose
Control unitMOVE
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
Position-based Visual Servoing (PBVS)Force and Visual Control for Safe Human−Robot Interaction 16/35
Position-based (3D) visual servoing scheme
Calibration dependent
Features extraction
Posecontrol
CameraRobot + motion control
Pose estimation
Desiredpose
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
PBVSForce and Visual Control for Safe Human−Robot Interaction 17/35
Pose control and pose estimation
Calibrated cameras Target objects of known geometry
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
Pose EstimationForce and Visual Control for Safe Human−Robot Interaction 18/35
Reconstruction of object pose from observed workspace
Observedworkspace
Image regionsegmentation
Image featuresextraction
Image acquisition
Pose reconstruction
Selection of image regions
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
Dynamic Image FeaturesForce and Visual Control for Safe Human−Robot Interaction 19/35
Pose estimation with dynamic image features selection Extended Kalman Filter (EKF) based on approximate object models
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
EKFForce and Visual Control for Safe Human−Robot Interaction 20/35
Extended Kalman Filter State-space model of the object motion
Output equation
Jacobian of the output equation
= input disturbance
= object pose
= measurement noise
~ image Jacobian
= image features parameters
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
Pose ReconstructionForce and Visual Control for Safe Human−Robot Interaction 21/35
Dynamic mode (interposing parts) A single BSP tree is generated on-
line, describing all the objects with respect to a common reference frame
For each camera, the visit algorithmis applied to the BSP tree
A Kalman filter is used for each object
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
Preselection AlgorithmForce and Visual Control for Safe Human−Robot Interaction 22/35
The preselection algorithm estimates the position of the projections of the object visible corners on
the image planes of each camera
~
~
Out of sight
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
Selection AlgorithmForce and Visual Control for Safe Human−Robot Interaction 23/35
A selection algorithm based on suitable quality indexes is employed to find the (sub)optimal set of (6 to 8) feature points
Some quality indexes for the cost function Spatial distribution (⇒ avoiding points concentration) Angular distribution (⇒ avoiding alignments) Camera distribution (⇒ triangulation) Anti-chattering (⇒ estimate noise reduction) Extraction reliability (⇒ robustness)
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
Features ExtractionForce and Visual Control for Safe Human−Robot Interaction 24/35
extracted corners
Out of sight
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
Visual Servoing ArchitectureForce and Visual Control for Safe Human−Robot Interaction 25/35
Robot CPU Servo CPU Power amplifiers
BUS VME
User interface modules
COMAU – C3G 9000 openRobot COMAU
SMART−3SFOLLOWER
Robot COMAU SMART−3S
LEADER
Board BIT 3
BUS AT
Board BIT 3
ControlPC
Control – PC (RePLiCS)
VisionPC
MATROX GENESIS
MATROX GENESIS
Vision – PC (VESPRO)
BUS AT
RS232SONY XC 8500 CE
SONY XC 8500 CE
(PDL2)
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
ExperimentsForce and Visual Control for Safe Human−Robot Interaction 26/35
FOLLOWER
LEADER
L-CameraR-Camera
Object
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
Extension to GraspingForce and Visual Control for Safe Human−Robot Interaction 27/35
Visually guided grasping Object in unstructured
environment Visual servoing Tracking of object motion Good reaction to uncertainties
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
Interaction ControlForce and Visual Control for Safe Human−Robot Interaction 28/35
Interaction control using vision and force Vision provides global information on surrounding environment to be used for motion
planning and obstacle avoidance Force allows adjusting robot motion so that local constraints imposed by environment
are satisfied
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
Force and Visual ControlForce and Visual Control for Safe Human−Robot Interaction 29/35
Set-up @ DLR KUKA robot with force sensor and
camera embedded in the gripper Integration of vision and force
Visual feedback in gross motion Force feedback in fine motion
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
Control StrategyForce and Visual Control for Safe Human−Robot Interaction 30/35
Problem Control interaction of a robot manipulator with a rigid object of
known geometry but unknown position and orientation
Solution When robot is far from object
Position-based visual servoing is adopted The relative pose of the robot with respect to the object is estimated recursively using only
vision When robot is in contact with object
Any kind of interaction control strategy can be adopted (impedance control, parallel force/position control)
The relative pose of the robot with respect to the object is estimated recursively using vision, force and joint position measurements
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
Visual ImpedanceForce and Visual Control for Safe Human−Robot Interaction 31/35
Position-based visual servoing
Force feedback
Impedance
impedance
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
Pose Estimation Using Vision and ForceForce and Visual Control for Safe Human−Robot Interaction 32/35
Modified EKF State-space model unchanged Modified output equation (when )
Modified Jacobian
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
ExperimentsForce and Visual Control for Safe Human−Robot Interaction 33/35
Pose estimation errors
vision vision & force
X
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
ConclusionForce and Visual Control for Safe Human−Robot Interaction 34/35
Interaction control of robot manipulators Indirect and direct force control Position-based visual servoing Position-based visual impedance control
Current and future work Interaction control in unstructured environments (presence of humans) Integration of new sensors (proximity sensors, joint torque sensors, …) Extension to dynamic manipulation (nonprehensile, deformable objects)
UPMC • Institut des Systèmes Intelligents et de Robotique Paris • 24 September 2015
Force and Visual Control for Safe Human−Robot Interaction 35/35
Thank You very much indeed for Your kind attention