ABSTRACT Robot learning from demonstration focuses on algorithms that enable a robot to learn a p... more ABSTRACT Robot learning from demonstration focuses on algorithms that enable a robot to learn a policy from demonstrations performed by a teacher, typically a human expert. This paper presents an experimental evaluation of two learning from demonstration algorithms, Interactive Reinforcement Learning and Behavior Networks. We evaluate the performance of these algorithms using a humanoid robot and discuss the relative advantages and drawbacks of these methods with respect to learning time, number of demonstrations, ease of implementation and other metrics. Our results show that Behavior Networks rely on a greater degree of domain knowledge and programmer expertise, requiring very precise definitions for behavior pre- and post-conditions. By contrast Interactive RL requires a relatively simple implementation based only on the robot's sensor data and actions. However, Behavior Networks leverage the pre-coded knowledge to effectively reduce learning time and the required number of human interactions to learn the task.
This work introduces Human-Agent Transfer (HAT), an algorithm that combines transfer learning, le... more This work introduces Human-Agent Transfer (HAT), an algorithm that combines transfer learning, learning from demonstration and reinforcement learning to achieve rapid learning and high performance in complex domains. Using experiments in a simulated robot soccer domain, we show that human demonstrations transferred into a baseline policy for an agent and refined using reinforcement learning significantly improve both learning time and policy performance. Our evaluation compares three algorithmic approaches to incorporating demonstration rule summaries into transfer learning, and studies the impact of demonstration quality and quantity, as well as the effect of combining demonstrations from multiple teachers. Our results show that all three transfer methods lead to statistically significant improvement in performance over learning without demonstration. The best performance was achieved by combining the best demonstrations from two teachers.
This paper presents the details of the curricular con-tent developed for a two-course robotics se... more This paper presents the details of the curricular con-tent developed for a two-course robotics sequence within the undergraduate Robotics Engineering pro-gram at Worcester Polytechnic Institute. The ap-proach focuses on teaching a unified robotics curricu-lum, incorporating the foundational concepts from computer science, electrical engineering and mechan-ical engineering, in an integrative manner by empha-sizing the whole system design. Outcomes include high student satisfaction, enhanced student learning and a broad engineering education to meet the needs of the growing robotics industry.
Humanoids 2008 - 8th IEEE-RAS International Conference on Humanoid Robots, 2008
Humanoid robots working alongside humans in everyday environments is a long standing goal of the ... more Humanoid robots working alongside humans in everyday environments is a long standing goal of the robotics community. To achieve this goal, methods for developing new robot behaviors that are intuitive and accessible to non-programmers are required. In this paper, we present a demonstration-based method for teaching distributed autonomous robots to coordinate their actions and perform collaborative multi-robot tasks. Within the
ABSTRACT This paper presents our progress toward a user guided manipulation framework for high de... more ABSTRACT This paper presents our progress toward a user guided manipulation framework for high degree-of-freedom robots operating in environments with limited communication. The system we propose consists of three components: (1) a user-guided perception interface that assists the user in providing task-level commands to the robot, (2) planning algorithms that autonomously generate robot motion while obeying relevant constraints, and (3) a trajectory execution and monitoring system which detects errors in execution. We report quantitative experiments performed on these three components and qualitative experiments of the entire pipeline with the PR2 robot turning a valve for the DARPA robotics challenge. We also describe how the framework was ported to the Hubo2+ robot with minimal changes which demonstrates its applicability to different types of robots.
Abstract: ndex number for the symbolic color to assign to the pixel or 0 if the pixelis backgroun... more Abstract: ndex number for the symbolic color to assign to the pixel or 0 if the pixelis background. The thresholds are learned from example images as describedin section 1.3. The color segmentation process uses the threshold table on eachpixel of the image to produce a color map (cmap) for the image (see Figure 1for the e#ect of this process). This
Proceedings of the 2014 ACM/IEEE international conference on Human-robot interaction - HRI '14, 2014
ABSTRACT Intelligent behavior in robots is implemented through algorithms. Historically, much of ... more ABSTRACT Intelligent behavior in robots is implemented through algorithms. Historically, much of algorithmic robotics research strives to compute outputs that achieve mathematically rigid conditions, such as minimizing path length. But today's robots are increasingly being used to empower the daily lives of people, and experience shows that traditional algorithmic approaches are poorly suited for the unpredictable, idiosyncratic, and adaptive nature of human-robot interaction. This raises a need for entirely new computational, mathematical, and technical approaches for robots to better understand and react to humans. The human-friendly robots of the future will need new algorithms, informed from the ground up by HRI research, to generate interpretable, ethical, socially-acceptable behavior, ensure safety around humans, and execute tasks of value to society.
ABSTRACT Robot learning from demonstration focuses on algorithms that enable a robot to learn a p... more ABSTRACT Robot learning from demonstration focuses on algorithms that enable a robot to learn a policy from demonstrations performed by a teacher, typically a human expert. This paper presents an experimental evaluation of two learning from demonstration algorithms, Interactive Reinforcement Learning and Behavior Networks. We evaluate the performance of these algorithms using a humanoid robot and discuss the relative advantages and drawbacks of these methods with respect to learning time, number of demonstrations, ease of implementation and other metrics. Our results show that Behavior Networks rely on a greater degree of domain knowledge and programmer expertise, requiring very precise definitions for behavior pre- and post-conditions. By contrast Interactive RL requires a relatively simple implementation based only on the robot's sensor data and actions. However, Behavior Networks leverage the pre-coded knowledge to effectively reduce learning time and the required number of human interactions to learn the task.
This work introduces Human-Agent Transfer (HAT), an algorithm that combines transfer learning, le... more This work introduces Human-Agent Transfer (HAT), an algorithm that combines transfer learning, learning from demonstration and reinforcement learning to achieve rapid learning and high performance in complex domains. Using experiments in a simulated robot soccer domain, we show that human demonstrations transferred into a baseline policy for an agent and refined using reinforcement learning significantly improve both learning time and policy performance. Our evaluation compares three algorithmic approaches to incorporating demonstration rule summaries into transfer learning, and studies the impact of demonstration quality and quantity, as well as the effect of combining demonstrations from multiple teachers. Our results show that all three transfer methods lead to statistically significant improvement in performance over learning without demonstration. The best performance was achieved by combining the best demonstrations from two teachers.
This paper presents the details of the curricular con-tent developed for a two-course robotics se... more This paper presents the details of the curricular con-tent developed for a two-course robotics sequence within the undergraduate Robotics Engineering pro-gram at Worcester Polytechnic Institute. The ap-proach focuses on teaching a unified robotics curricu-lum, incorporating the foundational concepts from computer science, electrical engineering and mechan-ical engineering, in an integrative manner by empha-sizing the whole system design. Outcomes include high student satisfaction, enhanced student learning and a broad engineering education to meet the needs of the growing robotics industry.
Humanoids 2008 - 8th IEEE-RAS International Conference on Humanoid Robots, 2008
Humanoid robots working alongside humans in everyday environments is a long standing goal of the ... more Humanoid robots working alongside humans in everyday environments is a long standing goal of the robotics community. To achieve this goal, methods for developing new robot behaviors that are intuitive and accessible to non-programmers are required. In this paper, we present a demonstration-based method for teaching distributed autonomous robots to coordinate their actions and perform collaborative multi-robot tasks. Within the
ABSTRACT This paper presents our progress toward a user guided manipulation framework for high de... more ABSTRACT This paper presents our progress toward a user guided manipulation framework for high degree-of-freedom robots operating in environments with limited communication. The system we propose consists of three components: (1) a user-guided perception interface that assists the user in providing task-level commands to the robot, (2) planning algorithms that autonomously generate robot motion while obeying relevant constraints, and (3) a trajectory execution and monitoring system which detects errors in execution. We report quantitative experiments performed on these three components and qualitative experiments of the entire pipeline with the PR2 robot turning a valve for the DARPA robotics challenge. We also describe how the framework was ported to the Hubo2+ robot with minimal changes which demonstrates its applicability to different types of robots.
Abstract: ndex number for the symbolic color to assign to the pixel or 0 if the pixelis backgroun... more Abstract: ndex number for the symbolic color to assign to the pixel or 0 if the pixelis background. The thresholds are learned from example images as describedin section 1.3. The color segmentation process uses the threshold table on eachpixel of the image to produce a color map (cmap) for the image (see Figure 1for the e#ect of this process). This
Proceedings of the 2014 ACM/IEEE international conference on Human-robot interaction - HRI '14, 2014
ABSTRACT Intelligent behavior in robots is implemented through algorithms. Historically, much of ... more ABSTRACT Intelligent behavior in robots is implemented through algorithms. Historically, much of algorithmic robotics research strives to compute outputs that achieve mathematically rigid conditions, such as minimizing path length. But today's robots are increasingly being used to empower the daily lives of people, and experience shows that traditional algorithmic approaches are poorly suited for the unpredictable, idiosyncratic, and adaptive nature of human-robot interaction. This raises a need for entirely new computational, mathematical, and technical approaches for robots to better understand and react to humans. The human-friendly robots of the future will need new algorithms, informed from the ground up by HRI research, to generate interpretable, ethical, socially-acceptable behavior, ensure safety around humans, and execute tasks of value to society.
Uploads
Papers by Sonia Chernova