Personal Robots
How to build socially engaging robots and interactive technologies that provide people with long-term social and emotional support to help people live healthier lives, connect with others, and learn better.
Robots are an intriguing technology that can straddle both the physical and social world of people. Inspired by animal and human behavior, our goal is to build capable robotic creatures with a "living" presence, and to gain a better understanding of how humans will interact with this new kind of technology. People will physically interact with them, communicate with them, understand them, and teach them, all in familiar human terms. Ultimately, such robots will possess the social savvy, physical adeptness, and everyday common sense to partake in people's daily lives in useful and rewarding ways.

Research Projects

  • 3DprintedClock

    Cynthia Breazeal, Peter Schmitt and Robert Swartz
    The 3DprintedClock project is the result of ready-assembled 3D printed computational mechanisms, and is related to research in the fields of rapid prototyping and digital fabrication. The clock was modeled in CAD software after an existing clock, and uses a weight and a pendulum to keep track of time. The CAD model was created according to the specifications of the 3D printer, assuring sufficient gaps and clearances for the different parts. In addition, support material, drainage, and perforations were added to allow for excess support material being removed after printing. The 3DprintedClock is intended to demonstrate the superior capabilities of 3D printing as a fabrication process. It should contribute toward the future use of 3D printers to replace injection molding and expensive tooling processes, and allow for on demand, customized, and “greener” consumer products.

  • AIDA: Affective Intelligent Driving Agent

    Cynthia Breazeal and Kenton Williams
    Humans are fundamentally social animals. Why not design cars to leverage this natural propensity for social interaction and understanding? We are working with Audi and the SENSEable City Lab to redefine the relationship between car, driver, and passengers. We are currently developing a new type of in-car system that acts as a partner or friend, providing important information, and intelligently responding to the mood and behavior of the driver.

  • Cloud-HRI

    Cynthia Breazeal, Nicholas DePalma, Adam Setapen and Sonia Chernova

    Imagine opening your eyes and being awake for only a half an hour at a time. This is the life that robots traditionally live. This is due to a number of factors such as battery life and wear on prototype joints. Roboticists have typically muddled though this challenge by crafting handmade models of the world or performing machine learning with synthetic data–and sometimes real-world data. While robotics researchers have traditionally used large distributed systems to do perception, planning, and learning, cloud-based robotics aims to link all of a robot's experiences. This movement aims to build large-scale machine learning algorithms that use experience from large groups of people, whether sourced from a large number of tabletop robots or a large number of experiences with virtual agents. Large-scale robotics aims to change embodied AI as it changed non-embodied AI.

  • Crowdsourcing Human-Robot Interaction: Online Game to Study Collaborative Human Behavior

    Cynthia Breazeal, Jason Alonso and Sonia Chernova

    Many new applications for robots require them to work alongside people as capable members of human-robot teams. We have developed Mars Escape, a two-player online game designed to study how humans engage in teamwork, coordination, and interaction. Data gathered from hundreds of online games is being used to develop computational models of human collaborative behavior in order to create an autonomous robot capable of acting as a reliable human teammate. In the summer of 2010, we will recreate the Mars Escape game in real life at the Boston Museum of Science and invite museum visitors to perform collaborative tasks together with the autonomous MDS robot Nexi.

    view site

  • DragonBot

    Adam Setapen, Natalie Freed, and Cynthia Breazeal

    DragonBot is a new platform built to support long-term interactions between children and robots. The robot runs entirely on an Android cell phone, which displays an animated virtual face. Additionally, the phone provides sensory input (camera and microphone) and fully controls the actuation of the robot (motors and speakers). Most importantly, the phone always has an Internet connection, so a robot can harness cloud-computing paradigms to learn from the collective interactions of multiple robots. To support long-term interactions, DragonBot is a "blended-reality" character–if you remove the phone from the robot, a virtual avatar appears on the screen and the user can still interact with the virtual character on the go. Costing less than $1,000, DragonBot was specifically designed to be a low-cost platform that can support longitudinal human-robot interactions "in the wild."

  • Exploring the Dynamics of Human-Robot Collaboration

    Cynthia Breazeal, Sigurdur Orn Adalgeirsson, Nicholas Brian DePalma, Jin Joo Lee, Philipp Robbel; Alborz Geramifard, Jon How, Julie Shah (CSAIL); Malte Jung and Pamela Hinds (Stanford)

    As robots become more and more capable, we will begin to invite them into our daily lives. There have been few examples of mobile robots able to carry out everyday tasks alongside humans. Though research on this topic is becoming more and more prevalent, we are just now beginning to understand what it means to collaborate. This project aims to unravel the dynamics involved in taking on leadership roles in collaborative tasks as well as balancing and maintaining the expectations of each member of the group (whether it be robot or human). This challenge involves aspects of inferring internal human state, role support and planning, as well as optimizing and keeping synchrony amongst team members "tight" in their collaboration.

  • Kombusto

    Adam Setapen, Natalie Freed, and Cynthia Breazeal

    Kombusto is the second character built around the DragonBot platform.

  • Le Fonduephone

    Natalie Freed, Adam Setapen, David Robert and Cynthia Breazeal

    Young children learn language not through listening alone, but through active communication with a social actor. Cultural immersion and context are also key in long-term language development. We are developing a robotic conversational partner and a hybrid physical/digital environment for second language learning. In "Le Fonduephone," a young child learns French by sitting down at a cafe table with a plush robotic character and ordering food together. The table is situated within a projected virtual environment that provides an animated backdrop. The character models how to order food and as the child practices the new vocabulary, the food is delivered via projections onto the table's surface. Meanwhile, a teacher observes the interaction remotely via a virtual representation of the cafe and can adjust the robot's conversation and behavior to support the learner.

  • NeverEnding Drawing Machine

    Edwina Portocarrero, V. Michael Bove Jr., Cynthia Breazeal, Glorianna Davenport, David Robert, Edwina Portocarrero, Sean Follmer and Michelle Chung

    Inspired by the Surrealists' Exquisite Corpse art game, the NeverEnding Drawing project is one of several applications developed on a scalable architecture and platform for collaborative creativity. Users co-create and edit each other's augmented sketchbooks in real time. By tracking individual pages of each live sketchbook, the system loads the appropriate background audiovisual content and enables users to add to it using a variety of real materials and means of mark-making. Users take pictures and record sounds to be sent back and forth between collaborators on the network. Additionally, the live sketchbooks facilitate non-linear, asynchronous access to the evolving, co-created content through their physical editing interface. By using crayons, colored pens, and various tactile and light-diffusing materials, the analog/digital hybrid model of content creation requires no expertise and creates a safe environment for sharing unfinished work with others.

    view site

  • Nimbus

    Adam Setapen and Cynthia Breazeal

    Nimbus is the first character built around the DragonBot platform, as an exploration into fabricating a believable and "cute" robotic character for children. Through building Nimbus, we learned many new techniques for creating lifelike characters around a robot's physical limitations and advantages. Many furry prototypes were made to support "squash-and-stretch"–the most important principle of animation that can bring inanimate characters to life. Also, fabric-based capacitive sensing was sewn into the fur, so Nimbus can detect when and where he is being touched. Nimbus was made completely in-house, using diverse fabrication techniques ranging from hand-machining mechanical linkages to designing and printing custom 3D parts.

  • originalMachines

    Cynthia Breazeal and Peter Schmitt

    The digital revolution has fundamentally changed our lives. Multimedia content-creation tools allow us to instantiate and share ideas easily, but most outcomes only exist on-screen and online--the physical world and everyday objects are largely excluded from a parallel explosion of mechatronic object creation. Services like Ponoko and Shapeways allow professionals and non-professionals to access computer-aided manufacturing (CAM) tools like 3D-printing and laser-cutting, but there are few (if any) design tools for creating complex mechanical assemblies that take full advantage of CAM systems. Creating unique mechatronic artifacts–Original Machines–thus requires more specific and sophisticated design tools than exist today. Object-oriented mechatronics is a parametric design approach that connects knowledge about mechanical assemblies and electronics with the requirements of digital manufacturing processes. The approach addresses the missing link between accessible rapid-manufacturing services and currently available design tools, creating new opportunities for self-expression through mechatronic objects and machines.

  • plywoodServo

    Peter Schmitt and Susanne Seitinger
    Animated artifacts require many different electronic and mechanical components, as well as appropriate drive software. This complexity has led to a kit-of-parts thinking in designing robotic assemblies, enabling more people to engage with animated devices. However, these robotics kits provide designers with a series of given constraints; the resulting black box becomes a form factor around which design is created rather than an integral part of the completed artifact, and these devices lack the specificity and material diversity of traditionally crafted artifacts. Many rapid prototyping tools propagate the same logic; for example, laser cutters are more frequently used to build casings that hide embedded mechanics and electronics than components that celebrate them. PlywoodServo considers a holistic approach to the design of animated artifacts in order to recapture the magic of engaging with their mechanical and electronic components together.

  • Robotic Textiles

    Adam Whiton

    We are investigating e-textiles and fiber-electronics to develop unique soft-architecture robotic components. We have been developing large area force sensors utilizing quantum tunneling composites integrated into textiles creating fabrics that can cover the body/surface of the robot and sense touch. By using e-textiles we shift from the metaphor of a sensing skin, often used in robotics, to one of sensing clothing. We incorporated apparel design and construction techniques to develop modular e-textile surfaces that can be easily attached to a robot and integrated into a robotic system. Adding new abilities to a robot system can become as simple as changing their clothes. Our goal is to study social touch interaction and communication between people and robots while exploring the benefits of textiles and the textile aesthetic.

  • Storytelling in the Preschool of Future

    Ryan Wistort

    Using the Preschool of the Future environment, children can create stories that come to life in the real world. We are developing interfaces that enable children to author stories in the physical environment—stories where robots are the characters and children are not only the observers, but also the choreographers and actors in the stories. To do this, children author stories and robot behaviors using a simple digital painting interface. By combining the physical affordances of painting with digital media and robotic characters, stories can come to life in the real world. Programming in this environment becomes a group activity when multiple children use these tangible interfaces to program advanced robot behaviors.

    view site

  • The Alphabots

    Cynthia Breazeal and David Robert

    The Alphabots are trans-fictional(xF) mobile and modular semi-autonomous robotic symbol set characters designed to play with preschool aged children (three to six years old). In support of early development goals (literacy, numeracy and shape recognition) educators and parents can take an active role in co-designing playful learning interactions both on and off-screen.

  • TinkRBook

    Cynthia Breazeal and Angela Chang
    TinkRBook is a storytelling system that introduces a new concept of reading, called textual tinkerability. Textual tinkerability uses storytelling gestures to expose the text-concept relationships within a scene. Tinkerability prompts readers to become more physically active and expressive as they explore concepts in reading together. TinkRBooks are interactive storybooks that prompt interactivity in a subtle way, enhancing communication between parents and children during shared picture-book reading. TinkRBooks encourage positive reading behaviors in emergent literacy: parents act out the story to control the words on-screen, demonstrating print referencing and dialogic questioning techniques. Young children actively explore the abstract relationship between printed words and their meanings, even before this relationship is properly understood. By making story elements alterable within a narrative, readers can learn to read by playing with how word choices impact the storytelling experience. Recently, this research has been applied to developing countries.

  • Zipperbot: Robotic Continuous Closure for Fabric Edge Joining

    Cynthia Breazeal and Adam Whiton

    In robotics, the emerging field of electronic textiles and fiber-electronics represents a shift in morphology from hard and rigid mechatronic components toward a soft-architecture–and more specifically, a flexible planar surface morphology. It is thus essential to determine how a robotic system might actuate flexible surfaces for donning and doffing actions. Zipperbot is a robotic continuous closure system for joining fabrics and textiles. By augmenting traditional apparel closure techniques and hardware with robotic attributes, we can incorporate these into robotic systems for surface manipulation. Through actuating closures, textiles could shape shift or self-assemble into a variety of forms.