DRRP on Robotics and Automation for Inclusive Transportation

Mission

• Transportation hubs, both large and small, serve as critical points in the travel chain. Due to their role as multi-modal nexus points, mobility breakdowns at hubs can impact large numbers of people across a wide range of disabilities. The DRRP on Robotics and Automation for Inclusive Transportation will research and develop seamless transportation assistance from cloud-based autonomy and shared robots located in and around transportation hubs.

Team

• Carnegie Mellon University
  Aaron Steinfeld (PI), Jeffery Bigham, Kris Kitani, John Zimmerman, & Anthony Tomasic
• University of Washington
  Anind Dey & Jennifer Mankoff
• R&D Partners
  Booz Allen Hamilton, Diyunu Consulting, & IBM Research Tokyo

Research Projects

• R1. Recognizing Travel Routines
  Project leads: Jen Mankoff, Anind K. Dey, & John Zimmerman
  We will use cloud-based autonomy to understand the routine behaviors associated with community travel. With models of these routine behaviors, we can reason about the choices that travelers with and without disabilities make in planning trips. Further, this will allow us to 1) predict how travelers can best get from place to place and overcome barriers and 2) enable the preemptive requests for service and assistance. Our overall goal is to improve the quality of a person with disabilities' transportation experience, even in the face of dynamic barriers.
• R2. Forward Assistance
  Project leads: John Zimmerman, Jeff Bigham, & Aaron Steinfeld
  In this project, we will investigate how to effectively intervene to aid travelers in overcoming barriers. Despite persistent effort, independent travel remains difficult for many people with disabilities, in part because of the unexpected barriers they encounter and fear of unexpected barriers. We will investigate what intervention should be delivered to help overcome these barriers, when it should be delivered, and how it should appear to the recipient.

Development Projects

• DV1. Characterize Pedestrian Environments
  Project leads: Kris Kitani, Jeff Bigham, & Chieko Asakawa (IBM/CMU)
  When navigating through a new environment, humans often use visual landmarks (furniture, signs, storefronts, etc) along our path to become familiar with the environment. This project’s goal is to extract and convey such landmarks for use by robots and assistive autonomy during navigation. In particular, we will refine and scale up VizMap, a knowledge map engine, which builds a virtual map of the 3D world and embeds it with meaningful semantic tags of important visual landmarks. We will use of state of the art computer vision and crowdsourcing to enable fully automatic object labeling and highly accurate user pose estimation. It will be used by robots and our existing open source NavCog navigation app to provide a more enhanced travel experience.
• DV2. Transportation Hub Assistance
  Project lead: Aaron Steinfeld
  This project will integrate the other three DRRP projects with the precursor NSF-funded Assistive Robots for Blind Travelers project to provide transportation assistance from cloud-based autonomy and shared robots located in and around a transportation hub in Pittsburgh. Example functionality in this deployment includes navigation assistance, robot guidance through a station, information retrieval, and rendezvous with services (e.g., station staff) and unmanned systems (e.g., shared robots, shared autonomous vehicles).

Stakeholder Involvement and the ATTRI Program

• This work will be guided by key domestic and international stakeholders, including representation from organizations serving people with disabilities, industry, and government.
• The project is part of the Accessible Transportation Technologies Research Initiative (ATTRI) within the "Robotics & Automation" technology development element. ATTRI is a joint USDOT initiative, co-led by the Federal Highway Administration (FHWA), Federal Transit Administration (FTA), and Intelligent Transportation Systems Joint Program Office (ITS JPO), with support from the National Institute on Disability, Independent Living, and Rehabilitation Research (NIDILRR), and other federal partners.

Collaborators

• Traffic21 & Metro21
• City of Pittsburgh
• Port Authority of Allegheny County
• US Army Research Laboratory (ARL) & US Army Tank Automotive Research Development and Engineering Center (TARDEC)
• The Arc of Greater Pittsburgh
• Blind & Vision Rehabilitation Services of Pittsburgh (BVRS)
• Sphero

Sponsor

• The Disability Rehabilitation Research Project (DRRP) on Robotics and Automation for Inclusive Transportation is funded under a grant from the National Institute on Disability, Independent Living, and Rehabilitation Research (NIDILRR grant number 90DPGE0003-01-00). NIDILRR is a Center within the Administration for Community Living (ACL), Department of Health and Human Services (HHS). The contents of this website do not necessarily represent the policy of NIDILRR, ACL, HHS, and you should not assume endorsement by the Federal Government.