Ellis Ratner
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Ellis Ratner has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Anca Diana Dragan
University of California, Berkeley, Berkeley, CA, USA
2 shared publications - Andrea Bajcsy
Carnegie Mellon University
2 shared publications - Claire J. Tomlin
University of California, Berkeley
2 shared publications - Benjamin J. Cohen
GRASP Laboratory, University of Pennsylvania, Philadelphia, 19104, USA
1 shared publication - Maxim Likhachev
Carnegie Mellon University
1 shared publication Mike Phillips
Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 15213, USA
1 shared publication
Latest Publications
- 18 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 6 (2) , 2373-2380
Efficient Dynamics Estimation With Adaptive Model Sets
Robotic systems frequently operate under changing dynamics, such as driving across varying terrain, encountering sensing and actuation faults, or navigating around humans with uncertain and changing intent. In order to operate effectively in these situations, robots must be capable of efficiently estimating these changes in order to adapt at the decision-making, planning, and control levels. Typical estimation approaches maintain a fixed set of candidate models at each time step; however, this can be computationally expensive if the number of models is large. In contrast, we propose a novel algorithm that employs an adaptive model set. We leverage the idea that the current model set must be expanded if its models no longer sufficiently explain the sensor measurements. By maintaining only a small subset of models at each time step, our algorithm improves on efficiency; at the same time, by choosing the appropriate models to keep, we avoid compromising on performance. We show that our algorithm exhibits higher efficiency in comparison to several baselines, when tested on simulated manipulation, driving, and human motion prediction tasks, as well as in hardware experiments on a 7 DOF manipulator.
- 18 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 6 (2) , 2373-2380
Efficient Dynamics Estimation With Adaptive Model Sets
Robotic systems frequently operate under changing dynamics, such as driving across varying terrain, encountering sensing and actuation faults, or navigating around humans with uncertain and changing intent. In order to operate effectively in these situations, robots must be capable of efficiently estimating these changes in order to adapt at the decision-making, planning, and control levels. Typical estimation approaches maintain a fixed set of candidate models at each time step; however, this can be computationally expensive if the number of models is large. In contrast, we propose a novel algorithm that employs an adaptive model set. We leverage the idea that the current model set must be expanded if its models no longer sufficiently explain the sensor measurements. By maintaining only a small subset of models at each time step, our algorithm improves on efficiency; at the same time, by choosing the appropriate models to keep, we avoid compromising on performance. We show that our algorithm exhibits higher efficiency in comparison to several baselines, when tested on simulated manipulation, driving, and human motion prediction tasks, as well as in hardware experiments on a 7 DOF manipulator.
- 30 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 6 (1) , 24-31
A Robust Control Framework for Human Motion Prediction
Designing human motion predictors which preserve safety while maintaining robot efficiency is an increasingly important challenge for robots operating in close physical proximity to people. One approach is to use robust control predictors that safeguard against every possible future human state, leading to safe but often too conservative robot plans. Alternatively, intent-driven predictors explicitly model how humans make decisions given their intent, leading to efficient robot plans. However, when the intent model is misspecified, the robot might confidently plan unsafe maneuvers. In this letter, we combine ideas from robust control and intent-driven human modelling to formulate a novel human motion predictor which provides robustness against misspecified human models, but reduces the conservatism of traditional worst-case predictors. Our approach predicts the human states by trusting the intent-driven model to decide only which human actions are completely unlikely. We then safeguard against all likely enough actions, much like a robust control predictor. We demonstrate in simulation and hardware how our approach safeguards against misspecified human intent models while not leading to overly conservative robot plans.
- 30 September 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 6 (1) , 24-31
A Robust Control Framework for Human Motion Prediction
Designing human motion predictors which preserve safety while maintaining robot efficiency is an increasingly important challenge for robots operating in close physical proximity to people. One approach is to use robust control predictors that safeguard against every possible future human state, leading to safe but often too conservative robot plans. Alternatively, intent-driven predictors explicitly model how humans make decisions given their intent, leading to efficient robot plans. However, when the intent model is misspecified, the robot might confidently plan unsafe maneuvers. In this letter, we combine ideas from robust control and intent-driven human modelling to formulate a novel human motion predictor which provides robustness against misspecified human models, but reduces the conservatism of traditional worst-case predictors. Our approach predicts the human states by trusting the intent-driven model to decide only which human actions are completely unlikely. We then safeguard against all likely enough actions, much like a robust control predictor. We demonstrate in simulation and hardware how our approach safeguards against misspecified human intent models while not leading to overly conservative robot plans.
- Open Access
- 1 May 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 9 (10504729) , 5523-5530
A web-based infrastructure for recording user demonstrations of mobile manipulation tasks
Learning from demonstration (LfD) is a common technique applied to many problems in robotics, such as populating grasp databases, training for reinforcement learning of high-level skill sets and bootstrapping motion planners. While such approaches are generally highly valued, they rely on the often time-consuming process of gathering user demonstrations, and hence it becomes difficult to attain a sizeable dataset. In this paper, we present a tool capable of recording large numbers of high-dimensional demonstrations of mobile manipulation tasks provided by non-experts in the field. Our tool accomplishes this via a web interface that requires no additional software to be installed beyond a web browser, as well as a scalable architecture that is capable of supporting 10 concurrent demonstrators on a single server. Our architecture employs a lightweight simulation environment to reduce unnecessary computations and improve performance. Furthermore, we show how our tool can be used to gather a large set of demonstrations of a mobile manipulation task by leveraging existing crowdsource platforms. The data set collected has been made available to the robotics community. We also present experiments in which we apply demonstrations collected through our infrastructure to teach a robot how to grasp, to teach a robot how to perform dexterous manipulation tasks such as scooping and to accelerate motion planning for full-body manipulation tasks.
- 1 May 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 9 (10504729) , 5523-5530
Open AccessA web-based infrastructure for recording user demonstrations of mobile manipulation tasks
Learning from demonstration (LfD) is a common technique applied to many problems in robotics, such as populating grasp databases, training for reinforcement learning of high-level skill sets and bootstrapping motion planners. While such approaches are generally highly valued, they rely on the often time-consuming process of gathering user demonstrations, and hence it becomes difficult to attain a sizeable dataset. In this paper, we present a tool capable of recording large numbers of high-dimensional demonstrations of mobile manipulation tasks provided by non-experts in the field. Our tool accomplishes this via a web interface that requires no additional software to be installed beyond a web browser, as well as a scalable architecture that is capable of supporting 10 concurrent demonstrators on a single server. Our architecture employs a lightweight simulation environment to reduce unnecessary computations and improve performance. Furthermore, we show how our tool can be used to gather a large set of demonstrations of a mobile manipulation task by leveraging existing crowdsource platforms. The data set collected has been made available to the robotics community. We also present experiments in which we apply demonstrations collected through our infrastructure to teach a robot how to grasp, to teach a robot how to perform dexterous manipulation tasks such as scooping and to accelerate motion planning for full-body manipulation tasks.