An official website of the United States government
Model-based optimal control of soft robots may enable compliant, underdamped platforms to operate in a repeatable fashion and effectively accomplish tasks that are otherwise impossible for soft robots. Unfortunately, developing accurate analytical dynamic models for soft robots is time-consuming, difficult, and error-prone. Deep learning presents an alternative modeling approach that only requires a time history of system inputs and system states, which can be easily measured or estimated. However, fully relying on empirical or learned models involves collecting large amounts of representative data from a soft robot in order to model the complex state space–a task which may not be feasible in many situations. Furthermore, the exclusive use of empirical models for model-based control can be dangerous if the model does not generalize well. To address these challenges, we propose a hybrid modeling approach that combines machine learning methods with an existing first-principles model in order to improve overall performance for a sampling-based non-linear model predictive controller. We validate this approach on a soft robot platform and demonstrate that performance improves by 52% on average when employing the combined model.
more »
« less
This content will become publicly available on April 7, 2027
Human Learning of Soft Robot Motion and Control: The Impact of Teaching Method and Task Order
Soft robotics has seen substantial success as a method to produce robust robot bodies which are safer for human users to interact with. However, while this means soft robots may be better suited to tasks requiring human interaction and teleoperation, little thought has been paid to how human users learn to control and leverage these soft robots. In pursuit of this goal, we conduct a pilot study investigating novice users interacting with a directly “operated” soft continuum robot in order to complete static and dynamic tasks in a range of difficulty levels. We study the effect of two features of the learning process: the teaching method (selfdirected versus structured) and the order of task presentation (easy to hard or hard to easy). Task performance and learning were assessed as measured by task completion time and success rate while user workload was directly measured through selfreport surveys and indirectly through heart rate tracking. We find that starting with harder tasks involving dynamic or multidegree of freedom motions better prepared users to transfer those skills to static pointing tasks. Similar benefits were partially achieved by structuring the teaching to highlight many of the robot’s features. These preliminary results highlight how soft robotic devices may require distinct teaching methods to avoid confusion or frustration by users, but that users are able to effectively explore the control space when given a sufficiently challenging context.
more »
« less
- Award ID(s):
- 2349067
- PAR ID:
- 10692830
- Publisher / Repository:
- IEEE
- Date Published:
- ISBN:
- 979-8-3315-8215-9
- Page Range / eLocation ID:
- 454 to 460
- Format(s):
- Medium: X
- Location:
- Kanazawa, Japan
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
There is significant interest in enabling robots to learn to perform tasks directly from interactions with non-expert users. Typically, a human serves as a teacher whose only task is to provide feedback to a robot learner. However, in real-world human-robot collaborations, the human often assists with the task while also offering feedback. Our key insight is that we can extract additional, implicit feedback from the human’s actions during the collaboration to augment the robot learning process. Under the assumption of fixed-role assignments, we first propose to formalize human preferences over a human-robot collaboration as a shared set of parameters encoding alignment between two reward functions: one that drives human behavior, and another that should direct robot behavior. This allows us to extract implicit feedback from an interaction by reasoning about the human’s actions in the task as actions that reveal the human’s preferences. Then, we combine this implicit feedback with traditional explicit human feedback to facilitate estimating the human’s preferences. We evaluated our proposed approach for Preference learning from Implicit and Explicit feedback (PIE) in simulations and with real users in a cooking scenario. Our simulation results indicate that combining multiple modalities of human feedback improves a robot’s ability to estimate human preferences over the collaboration, with a similar trend observed in real-world evaluations. These findings highlight a promising direction for enabling robots to adapt to a user’s preference model more quickly, thereby reducing the amount of time a person must spend teaching a robot.more » « less
-
In the field of Human-Robot Interaction, researchers often techniques such as the Wizard-of-Oz paradigms in order to better study narrow scientific questions while carefully controlling robots’ capabilities unrelated to those questions, especially when those other capabilities are not yet easy to automate. However, those techniques often impose limitations on the type of collaborative tasks that can be used, and the perceived realism of those tasks and the task context. In this paper, we discuss how Augmented Reality can be used to address these concerns while increasing researchers’ level of experimental control, and discuss both advantages and disadvantages of this approachmore » « less
-
Physical interaction between humans and robots can help robots learn to perform complex tasks. The robot arm gains information by observing how the human kinesthetically guides it throughout the task. While prior works focus on how the robot learns, it is equally important that this learning is transparent to the human teacher. Visual displays that show the robot’s uncertainty can potentially communicate this information; however, we hypothesize that visual feedback mechanisms miss out on the physical connection between the human and robot. In this work we present a soft haptic display that wraps around and conforms to the surface of a robot arm, adding a haptic signal at an existing point of contact without significantly affecting the interaction. We demonstrate how soft actuation creates a salient haptic signal while still allowing flexibility in device mounting. Using a psychophysics experiment, we show that users can accurately distinguish inflation levels of the wrapped display with an average Weber fraction of 11.4%. When we place the wrapped display around the arm of a robotic manipulator, users are able to interpret and leverage the haptic signal in sample robot learning tasks, improving identification of areas where the robot needs more training and enabling the user to provide better demonstrations. See videos of our device and user studies here: https://youtu.be/tX-2Tqeb9Nwmore » « less
-
Accurate shape reconstruction is essential for precise control and reliable operation of soft robots. Compared to sensor-based approaches, vision-based methods offer advantages in cost, simplicity, and ease of deployment. However, existing vision-based methods often rely on complex camera setups, specific backgrounds, or large-scale training datasets, limiting their practicality in real-world scenarios. In this work, we propose a vision-based, markerless, and training-free framework for soft robotic shape reconstruction that directly leverages the natural surface appearance of the robot. These surface features act as implicit visual markers, enabling a hierarchical matching strategy that decouples local partition alignment from global kinematic optimization. Requiring only an initial 3D reconstruction and kinematic alignment, our method achieves real-time shape tracking across diverse environments while maintaining robustness to occlusions and variations in camera viewpoints. Experimental validation on a continuum soft robot demonstrates an average tip error of 2.6% during real-time operation, as well as stable performance in practical closed-loop control tasks. These results highlight the potential of the proposed approach for reliable, low-cost deployment in dynamic real-world settings.more » « less
