Scholarly Works, Mechanical Engineering
Permanent URI for this collection
Research articles, presentations, and other scholarship
Browse
Browsing Scholarly Works, Mechanical Engineering by Subject "0801 Artificial Intelligence and Image Processing"
Now showing 1 - 4 of 4
Results Per Page
Sort Options
- An Autonomous Task Assignment Paradigm for Autonomous Robotic In-Space AssemblyHildebrand, Robert; Komendera, Erik; Moser, Joshua; Hoffman, Julia (Frontiers, 2022-02-25)The development of autonomous robotic systems is a key component in the expansion of space exploration and the development of infrastructures for in-space applications. An important capability for these robotic systems is the ability to maintain and repair structures in the absence of human input by autonomously generating valid task sequences and task to robot allocations. To this end, a novel stochastic problem formulation paired with a mixed integer programming assembly schedule generator has been developed to articulate the elements, constraints, and state of an assembly project and solve for an optimal assembly schedule. The developed formulations were tested with a set of hardware experiments that included generating an optimal schedule for an assembly and rescheduling during an assembly to plan a repair. This formulation and validation work provides a path forward for future research in the development of an autonomous system capable of building and maintaining in-space infrastructures.
- Learning latent actions to control assistive robotsLosey, Dylan P.; Jeon, Hong Jun; Li, Mengxi; Srinivasan, Krishnan; Mandlekar, Ajay; Garg, Animesh; Bohg, Jeannette; Sadigh, Dorsa (Springer, 2021-08-04)Assistive robot arms enable people with disabilities to conduct everyday tasks on their own. These arms are dexterous and high-dimensional; however, the interfaces people must use to control their robots are low-dimensional. Consider teleoperating a 7-DoF robot arm with a 2-DoF joystick. The robot is helping you eat dinner, and currently you want to cut a piece of tofu. Today’s robots assume a pre-defined mapping between joystick inputs and robot actions: in one mode the joystick controls the robot’s motion in the x–y plane, in another mode the joystick controls the robot’s z–yaw motion, and so on. But this mapping misses out on the task you are trying to perform! Ideally, one joystick axis should control how the robot stabs the tofu, and the other axis should control different cutting motions. Our insight is that we can achieve intuitive, user-friendly control of assistive robots by embedding the robot’s high-dimensional actions into low-dimensional and human-controllable latent actions. We divide this process into three parts. First, we explore models for learning latent actions from offline task demonstrations, and formalize the properties that latent actions should satisfy. Next, we combine learned latent actions with autonomous robot assistance to help the user reach and maintain their high-level goals. Finally, we learn a personalized alignment model between joystick inputs and latent actions. We evaluate our resulting approach in four user studies where non-disabled participants reach marshmallows, cook apple pie, cut tofu, and assemble dessert. We then test our approach with two disabled adults who leverage assistive devices on a daily basis.
- Learning reward functions from diverse sources of human feedback: Optimally integrating demonstrations and preferencesBıyık, Erdem; Losey, Dylan P.; Palan, Malayandi; Landolfi, Nicholas C.; Shevchuk, Gleb; Sadigh, Dorsa (SAGE, 2022-01)Reward functions are a common way to specify the objective of a robot. As designing reward functions can be extremely challenging, a more promising approach is to directly learn reward functions from human teachers. Importantly, data from human teachers can be collected either passively or actively in a variety of forms: passive data sources include demonstrations (e.g., kinesthetic guidance), whereas preferences (e.g., comparative rankings) are actively elicited. Prior research has independently applied reward learning to these different data sources. However, there exist many domains where multiple sources are complementary and expressive. Motivated by this general problem, we present a framework to integrate multiple sources of information, which are either passively or actively collected from human users. In particular, we present an algorithm that first utilizes user demonstrations to initialize a belief about the reward function, and then actively probes the user with preference queries to zero-in on their true reward. This algorithm not only enables us combine multiple data sources, but it also informs the robot when it should leverage each type of information. Further, our approach accounts for the human’s ability to provide data: yielding user-friendly preference queries which are also theoretically optimal. Our extensive simulated experiments and user studies on a Fetch mobile manipulator demonstrate the superiority and the usability of our integrated framework.
- Physical interaction as communication: Learning robot objectives online from human correctionsLosey, Dylan P.; Bajcsy, Andrea; O'Malley, Marcia K.; Dragan, Anca D. (SAGE, 2021-10-25)When a robot performs a task next to a human, physical interaction is inevitable: the human might push, pull, twist, or guide the robot. The state of the art treats these interactions as disturbances that the robot should reject or avoid. At best, these robots respond safely while the human interacts; but after the human lets go, these robots simply return to their original behavior. We recognize that physical human–robot interaction (pHRI) is often intentional: the human intervenes on purpose because the robot is not doing the task correctly. In this article, we argue that when pHRI is intentional it is also informative: the robot can leverage interactions to learn how it should complete the rest of its current task even after the person lets go. We formalize pHRI as a dynamical system, where the human has in mind an objective function they want the robot to optimize, but the robot does not get direct access to the parameters of this objective: they are internal to the human. Within our proposed framework human interactions become observations about the true objective. We introduce approximations to learn from and respond to pHRI in real-time. We recognize that not all human corrections are perfect: often users interact with the robot noisily, and so we improve the efficiency of robot learning from pHRI by reducing unintended learning. Finally, we conduct simulations and user studies on a robotic manipulator to compare our proposed approach with the state of the art. Our results indicate that learning from pHRI leads to better task performance and improved human satisfaction.