Title: Domo: Manipulation for Partner Robots Aaron Edsinger MIT Computer Science and Artificial Intelligence Laboratory Humanoid Robotics Group edsinger@csail.mit.edu
1Domo Manipulation for Partner RobotsAaron
EdsingerMIT Computer Science and Artificial
Intelligence LaboratoryHumanoid Robotics
Groupedsinger_at_csail.mit.edu
2Robots That Can Work Alongside Humans
- Built for human environments
- Safety in the human workspace
- Humanoid body to work with everday objects
- Perform tasks that are important to people using
natural strategies with everyday objects
3Confronting Unstructured Environments
4Creating Robust Manipulation Interactions in
Unstructured Environments
- Let the body assist perception
- Passive compliance and force control
- Highly integrated behavior-based architecture
- Perceptual prediction through efference-copy
models - Learn task-relevant features of objects instead
of using full 3D models
5Domo
- 29 active degrees of freedom (DOF)
- Two 6 DOF force controlled arms using Series
Elastic Actuators - Two 6 DOF force controlled hands using SEAs
- A 2 DOF force controlled neck using SEAs
- Stereo pair of Point Grey Firewire CCD cameras
- Stereo Videre STH-DCSG-VAR-C Firewire cameras
- Intersense 3 axis gyroscope
- Two 4 DOF hands using Force Sensing Compliant
(FSC) actuators - Embedded brushless and brushed DC motor drivers
- 5 Embedded Motorola 56F807 DSPs running a 1khz
control loop
6Behavior Based Architecture
Arm Behaviors
Head Behaviors
7Series Elastic and Force Sensing Compliant
Actuators
F-kx
8Series Elastic and Force Sensing Compliant
Actuators
- Mechanically simple
- Improved stability
- Shock tolerance
- Highly backdrivable
- Low-grade components
- Low impedance at high frequencies
9Passive and Active Compliance
- Series Elastic Actuator Force based
grasping
10Efference Copy Model
Exploit interaction forces at the hand as an
additional perceptual modality
Upper 4 DOF of each arm.
Sensed joint torque
Sensed joint angle
Jacobian relates hand forces to joint torques
11Efference Copy Model
Sensed torque
Bimanual interaction torque
- Simplified inverse dynamic model of arm
- Model predicts normally occurring torques during
reaching - Use the prediction to amplify the salience of
interaction torques (external and bimanual)
External interaction torque
Mass Acceleration torque
Motor torque
Inverse dynamics
0
Coriolis and Centrifugal
Predicted torque
Known (Commanded torque)
Sensed torque
Commanded torque
Known
(von Holst, 1973)
12Detection of Self-Induced Hand Forces
Interaction forces at hands are approximately
equal and opposite
Interaction forces present
Interaction forces not present
13Detection of Interaction Forces
Ballistic reaching prediction error
Efference copy model generates torque
prediction. Torque prediction errors
drive visual attention system.
External forces prediction error
14Learning About Tool Use
- Motion feature points for tip detection
- 3D position estimation using probabilistic model
15Estimation of Tool Position in the Hand
16Autonomous Detection and Control ofHuman Tools