Research Approach

Robots that work alongside us in our homes and workplaces could extend
the time an elderly person can live at home, provide physical assistance to a worker on an assembly line, or help with household chores. In order to assist us in these ways, robots will need to successfully perform manipulation tasks within human environments. Human environments present special challenges for robot
manipulation since they are complex, dynamic, uncontrolled, and difficult to perceive reliably.

In our work with Domo, there are three themes that characterize our approach to manipulation in human environments. The first theme, cooperative manipulation, refers to the advantages that can be gained by having the robot work with a person to cooperatively perform manipulation tasks. The second theme, task relevant features, emphasizes the benefits of carefully selecting the aspects
of the world that are to be perceived and acted upon during a manipulation task. The third theme, let the body do the thinking, encompasses several ways in which a robot can use its body to simplify manipulation tasks.

Domo is unique in that it has compliant, force sensing actuators (SEA) through out its body from the neck down. These actuators tradeoff precise, stiff position control for safe, compliant force control. In doing so, they allow for safe human interaction with the robot. Many of today's robots can be dangerous around people and are poorly suited for use in human environments. Domo's hardware allows investigation of fundametal research issues surrounding manipulation. Namely, how to integrate visual perception, compliant manipulator control, and safe human-robot collaboration in order to accomplish useful manipulation tasks without releying upon complex perceptual modelling and explicit planning.

 

 

 

 

 

 

 

 

 

 

 

Manipulation in Human Environments

Robots that work alongside us in our homes and workplaces could extend the time an elderly person can live at
home, provide physical assistance to a worker on an assembly line, or help with household chores. In order to assist us in
these ways, robots will need to successfully perform manipulation tasks within human environments. Human environments present
special challenges for robot manipulation since they are complex, dynamic, uncontrolled, and difficult to perceive reliably.
In this paper we present a behavior-based control system that enables a humanoid robot, Domo, to help a person place objects
on a shelf. Domo is able to physically locate the shelf, socially cue a person to hand it an object, grasp the object that has been
handed to it, transfer the object to the hand that is closest to the shelf, and place the object on the shelf. We use this behavior-based control system to illustrate three themes that characterize our approach to manipulation in human environments. The first theme, cooperative manipulation, refers to the advantages that can be gained by having the robot work with a person to cooperatively perform manipulation tasks. The second theme, task relevant features, emphasizes the benefits of carefully selecting the aspects of the world that are to be perceived and acted upon during a manipulation task. The third theme, let the body do the thinking, encompasses several ways in which a robot can use its body to simplify manipulation tasks.

Edsinger, Aaron and Kemp, Charles C. "Manipulation in Human Environments". Proceedings of the IEEE/RSJ International Conference on Humanoid Robotics, 2006.[PDF]

 

Toward Robot Learning of Tool Manipulation from Human Demonstration

Robots that manipulate everyday tools in unstructured, human settings could more easily work with people and perform tasks that are
important to people. Task demonstration could serve as an intuitive way for people to program robots to perform tasks. By focusing on
task-relevant features during both the demonstration and the execution of a task, a robot could more robustly emulate the important
characteristics of the task and generalize what it has learned. In this paper we describe a method for robot task learning that makes use
of the perception and control of the tip of a tool. For this approach, the robot monitors the tool's tip during human use, extracts the
trajectory of this task relevant feature, and then manipulates the tool by controlling this feature. We present preliminary results
where a humanoid robot learns to clean a flexible hose with a brush. This task is accomplished in an unstructured environment
without prior models of the objects or task

Edsinger, Aaron and Kemp, Charles C. "Toward Robot Learning of Tool Manipulation from Human Demonstration". Unpublished 2006.[PDF]

The Development of Visual Categories for a Robot's Body and the World that it Influences

We present a developmental perceptual system for a humanoid robot that autonomously discovers its hand from less than 2 minutes of natural interaction with a human. The perceptual system combines simple proprioceptive sensing with a visual attention system that uses motion to select salient regions. We show that during natural interactions with a person, the majority of the selected visual regions consist of significant body parts on the human and robot (hands, fingers, and the human's head). The system visually clusters the selected image regions, models their spatial distribution over a sensory sphere, and uses mutual information to determine how much the clusters are influenced by the robot's arm. In our tests, the visual cluster that most strongly relates to the robot's arm primarily contains images of the robot's hand, and has a spatial distribution that can predict the location of the robot's hand in the image as a function of the arm's configuration.

Kemp, Charles C. and Edsinger, Aaron. "What Can I Control?: The Development of Visual Categories for a Robot's Body and the World that it Influences". Proceedings of the Fifth International Conference on Development and Learning, Special Session on Autonomous Mental Development. 2006.[PDF]

 

Autonomous Detection and Control of Task Relevant Features

The efficient acquisition and generalization of skills for manual tasks requires that a robot be able to perceive and control the
important aspects of an object while ignoring irrelevant factors. For many tasks involving everyday tool-like objects, detection and control of the distal end of the object is sufficient for its use. For example, a robot could pour a substance from a bottle by controlling
the position and orientation of the mouth. Likewise, the canonical tasks associated with a screwdriver, hammer, or pen rely on control
of the tool's tip. In this paper, we present methods that allow a robot to autonomously detect and control the tip of a tool-like
object. We also show results for modeling the appearance of this important type of task relevant feature.

Kemp, Charles C. and Edsinger, Aaron. "Robot Manipulation of Human Tools: Autonomous Detection and Control of Task Relevant Features". Proceedings of the Fifth International Conference on Development and Learning, Special Session on Classifying Activities in Manual Tasks. 2006.[PDF]

Visual Tool Tip Detection and Position Estimation

Robots that use human tools could more easily work with people, per form tasks that are important to people, and benefit from human strategies for accomplishing these tasks. For a wide variety of tools and tasks, control of the tool's endpoint is sufficient for its use. In this paper we present a straight-forward method for rapidly detecting the endpoint of an unmodeled tool and estimating its position with respect to the robot's hand. The robot rotates the tool while using optical flow to detect the most rapidly moving image points, and then finds the 3D position with respect to its hand that best explains these noisy 2D detections. The resulting 3D position estimate allows the robot to control the position of the tool endpoint and predict its visual location. We show successful results for this method using a humanoid robot with a variety of traditional tools, including a pen, a hammer, and pliers, as well as more general tools such as a bottle and the robot's own finger.

Kemp, Charles C. and Edsinger, Aaron. "Visual Tool Tip Detection and Position Estimation for Robotic Manipulation of Unknown Human Tools", Massachusetts Institute of Technology, CSAIL, Tech. Report AIM-2005-037 [PDF]

Ego-Exo Discrimination

Ego-exo discrimination can be seen as a basic underpinning in the formulation of a notion of the ``ecological self''. The ecological self is a physically embodied representation of the self, derived from the direct relationships between the body and its environment. The representation is constructed through explorations and interactions in the world. It is our position that on a robot, an ecological self should be be constructed over time, according to a developmental plan. Early, simple exploratory behaviors can generate the sensorimotor experiences necessary to scaffold further stages in the construction. One step in such a developmental approach for a humanoid robot is to incorporate, at the lowest level, the notion of ego-exo discrimination.

Edsinger-Gonzales, Aaron. "Developmentally Guided Ego-Exo Force Discrimination for a Humanoid Robot ", In submission: Fifth International Workshop on Epigenetic Robotics. Nara, Japan, 2005. [PDF]

Domo Design.

Humanoid robots found in research and commercial use today typically lack the ability to operate in unstructured and unknown environments. Force sensing and compliance at each robot joint can allow the robot to safely act in these environments. However, these features can be difficult to incorporate into robot designs. We present a new force sensing and compliant humanoid under development in the Humanoid Robotics Group at MIT CSAIL. The robot, named, Domo, is to be a research platform for exploring issues in general dexterous manipulation, visual perception, and learning. In this paper we describe aspects of the design, detail proposed research directions for the robot, and illustrate how the design of humanoid robots can be informed by the desired research goals.

Edsinger-Gonzales, Aaron and Jeff Weber. "Domo: A Force Sensing Humanoid Robot for Manipulation Research", Proceedings of the IEEE/RSJ International Conference on Humanoid Robotics, 2004. [PDF]

Hand Design.

Robot manipulation tasks in unknown and unstructured environments can often be better addressed with hands that are capable of
force-sensing and passive compliance. We describe the design of a compact four degree-of-freedom (DOF) hand that exhibits these
properties. This hand is being developed for a new humanoid robot platform.

Edsinger-Gonzales, Aaron . "Design of a Compliant and Force Sensing Hand for a Humanoid Robot", Proceedings of the International Conference on Intelligent Manipulation and Grasping, 2004. [PDF]