Reid Simmons
Research Professor | Carnegie Mellon University
Pittsburgh, PA, UNITED STATES
Reid Simmons has been developing robot systems that can work reliably in unstructured, unknown environments.
Biography
A researcher in autonomous mobile robots, Reid Simmons has been developing robot systems that can work reliably in unstructured, unknown environments. He also works in multi-robot systems and human-robot interaction. His areas of specialty include: robotics, Artificial Intelligence, autonomy, architectures for autonomous systems, robot navigation, multi-robot systems and human-robot interaction. Reid is the director of the JPMorgan Chase & Co. AI Maker Space at CMU.
Areas of Expertise (6)
Robotics
Robot Navigation
Artificial Intelligence
Multi-Robot Systems
Human-Robot Interaction
Autonomous Systems
Media Appearances (5)
CMU opens first AI maker space to let students ‘sharpen the cutting edge of AI’
Pittsburgh Post-Gazette online
2021-11-10
"We want students from all over the university — from engineering, business and fine arts — to come and use their creativity to make interesting things happen," Simmons said. "Giving students the freedom to let their imaginations run wild is really what this space is all about."
CMU Puts AI To Work in New NSF-funded Institutes
Carnegie Mellon University online
2021-07-30
"What we're trying to do is collaborate. We're not replacing caregivers; we're augmenting their capabilities," Simmons said. "The AI has to adapt to the individual and even more so, it has to adapt to the network the individual is in. We're intending that the AI is going to be assisting people over a long time, and while there will be plenty of time for the system to learn, there will also be plenty to learn."
The Salad Days of AI
Carnegie Mellon University online
2020-12-17
Reid Simmons, who teaches the course with Stephanie Rosenthal, said using AI to grow vegetables is a good way for students to put the knowledge of AI-based autonomous agents that they learned in class into practice. Agents have applications in many areas, such as self-driving cars, intelligent factories and smart homes. Another — automated greenhouses — proved a good match to the need for a course exercise.
What the country’s first undergrad program in artificial intelligence will look like
EdScoop online
2018-05-17
The Pittsburgh-based university already offers nearly two dozen courses in AI and related fields, said Reid Simmons, a Carnegie Mellon research professor who is currently on leave for the year while he works at the National Science Foundation.
This Scrabble-Playing Robot Is a Sore Loser
The Wall Street Journal online
2014-03-16
"Sometimes, I hate this game," says Victor, a Scrabble-playing robot created by students under the supervision of Reid Simmons, a robotics professor at Carnegie Mellon University here. Victor's secret is that he talks a better game than he plays. He is a champion trash talker. A typical put-down: "Since you're human, I guess you think that's a pretty good move."
Industry Expertise (1)
Computer Hardware
Education (3)
Massachusetts Institute of Technology: Ph.D., Computer Science 1998
Massachusetts Institute of Technology: M.S., Computer Science
University of Buffalo: B.S., Computer Science 1979
Links (3)
Articles (4)
The Role of Adaptation in Collective Human–AI Teaming
Topics in Cognitive Science2022 This paper explores a framework for defining artificial intelligence (AI) that adapts to individuals within a group, and discusses the technical challenges for collaborative AI systems that must work with different human partners. Collaborative AI is not one‐size‐fits‐all, and thus AI systems must tune their output based on each human partner's needs and abilities. For example, when communicating with a partner, an AI should consider how prepared their partner is to receive and correctly interpret the information they are receiving. Forgoing such individual considerations may adversely impact the partner's mental state and proficiency. On the other hand, successfully adapting to each person's (or team member's) behavior and abilities can yield performance benefits for the human–AI team.
Machine teaching for human inverse reinforcement learning
Frontiers in Robotics and AI2021 As robots continue to acquire useful skills, their ability to teach their expertise will provide humans the two-fold benefit of learning from robots and collaborating fluently with them. For example, robot tutors could teach handwriting to individual students and delivery robots could convey their navigation conventions to better coordinate with nearby human workers. Because humans naturally communicate their behaviors through selective demonstrations, and comprehend others’ through reasoning that resembles inverse reinforcement learning (IRL), we propose a method of teaching humans based on demonstrations that are informative for IRL. But unlike prior work that optimizes solely for IRL, this paper incorporates various human teaching strategies (e.g. scaffolding, simplicity, pattern discovery, and testing) to better accommodate human learners.
Detection and correction of subtle context-dependent robot model inaccuracies using parametric regions
The International Journal of Robotics Research2019 Autonomous robots frequently rely on models of their sensing and actions for intelligent decision making. Unfortunately, in complex environments, robots are bound to encounter situations in which their models do not accurately represent the world. Furthermore, these context-dependent model inaccuracies may be subtle, such that multiple observations may be necessary to distinguish them from noise. This paper formalizes the problem of detection and correction of such subtle contextual model inaccuracies in autonomous robots, and presents an algorithm to address this problem. The solution relies on reasoning about these contextual inaccuracies as parametric regions of inaccurate modeling (RIMs) in the robot’s planning space.
A receptionist robot for Brazilian people: study on interaction involving illiterates
Paladyn, Journal of Behavioral Robotics2017 The receptionist job, consisting in providing useful indications to visitors in a public office, is one possible employment of social robots. The design and the behaviour of robots expected to be integrated in human societies are crucial issues, and they are dependent on the culture and society in which the robot should be deployed. We study the factors that could be used in the design of a receptionist robot in Brazil, a country with a mix of races and considerable gaps in economic and educational level. This inequality results in the presence of functional illiterate people, unable to use reading, writing and numeracy skills. We invited Brazilian people, including a group of functionally illiterate subjects, to interact with two types of receptionists differing in physical appearance (agent v mechanical robot) and in the sound of the voice (human like v mechanical).
Social