Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userInforming Real-time Corrections in Corrective Shared Autonomy Through Expert Demonstrations
342
0
0.0
(
0
)
Added by
Michael Hagenow
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Corrective Shared Autonomy is a method where human corrections are layered on top of an otherwise autonomous robot behavior. Specifically, a Corrective Shared Autonomy system leverages an external controller to allow corrections across a range of task variables (e.g., spinning speed of a tool, applied force, path) to address the specific needs of a task. However, this inherent flexibility makes the choice of what corrections to allow at any given instant difficult to determine. This choice of corrections includes determining appropriate robot state variables, scaling for these variables, and a way to allow a user to specify the corrections in an intuitive manner. This paper enables efficient Corrective Shared Autonomy by providing an automated solution based on Learning from Demonstration to both extract the nominal behavior and address these core problems. Our evaluation shows that this solution enables users to successfully complete a surface cleaning task, identifies different strategies users employed in applying corrections, and points to future improvements for our solution.
rate research
Read More
Many tasks, particularly those involving interaction with the environment, are characterized by high variability, making robotic autonomy difficult. One flexible solution is to introduce the input of a human with superior experience and cognitive abilities as part of a shared autonomy policy. However, current methods for shared autonomy are not designed to address the wide range of necessary corrections (e.g., positions, forces, execution rate, etc.) that the user may need to provide to address task variability. In this paper, we present corrective shared autonomy, where users provide corrections to key robot state variables on top of an otherwise autonomous task model. We provide an instantiation of this shared autonomy paradigm and demonstrate its viability and benefits such as low user effort and physical demand via a system-level user study on three tasks involving variability situated in aircraft manufacturing.
Shared autonomy enables robots to infer user intent and assist in accomplishing it. But when the user wants to do a new task that the robot does not know about, shared autonomy will hinder their performance by attempting to assist them with something that is not their intent. Our key idea is that the robot can detect when its repertoire of intents is insufficient to explain the users input, and give them back control. This then enables the robot to observe unhindered task execution, learn the new intent behind it, and add it to this repertoire. We demonstrate with both a case study and a user study that our proposed method maintains good performance when the humans intent is in the robots repertoire, outperforms prior shared autonomy approaches when it isnt, and successfully learns new skills, enabling efficient lifelong learning for confidence-based shared autonomy.
We propose Automatic Curricula via Expert Demonstrations (ACED), a reinforcement learning (RL) approach that combines the ideas of imitation learning and curriculum learning in order to solve challenging robotic manipulation tasks with sparse reward functions. Curriculum learning solves complicated RL tasks by introducing a sequence of auxiliary tasks with increasing difficulty, yet how to automatically design effective and generalizable curricula remains a challenging research problem. ACED extracts curricula from a small amount of expert demonstration trajectories by dividing demonstrations into sections and initializing training episodes to states sampled from different sections of demonstrations. Through moving the reset states from the end to the beginning of demonstrations as the learning agent improves its performance, ACED not only learns challenging manipulation tasks with unseen initializations and goals, but also discovers novel solutions that are distinct from the demonstrations. In addition, ACED can be naturally combined with other imitation learning methods to utilize expert demonstrations in a more efficient manner, and we show that a combination of ACED with behavior cloning allows pick-and-place tasks to be learned with as few as 1 demonstration and block stacking tasks to be learned with 20 demonstrations.
Human input has enabled autonomous systems to improve their capabilities and achieve complex behaviors that are otherwise challenging to generate automatically. Recent work focuses on how robots can use such input - like demonstrations or corrections - to learn intended objectives. These techniques assume that the humans desired objective already exists within the robots hypothesis space. In reality, this assumption is often inaccurate: there will always be situations where the person might care about aspects of the task that the robot does not know about. Without this knowledge, the robot cannot infer the correct objective. Hence, when the robots hypothesis space is misspecified, even methods that keep track of uncertainty over the objective fail because they reason about which hypothesis might be correct, and not whether any of the hypotheses are correct. In this paper, we posit that the robot should reason explicitly about how well it can explain human inputs given its hypothesis space and use that situational confidence to inform how it should incorporate human input. We demonstrate our method on a 7 degree-of-freedom robot manipulator in learning from two important types of human input: demonstrations of manipulation tasks, and physical corrections during the robots task execution.
We present a system to infer and execute a human-readable program from a real-world demonstration. The system consists of a series of neural networks to perform perception, program generation, and program execution. Leveraging convolutional pose machines, the perception network reliably detects the bounding cuboids of objects in real images even when severely occluded, after training only on synthetic images using domain randomization. To increase the applicability of the perception network to new scenarios, the network is formulated to predict in image space rather than in world space. Additional networks detect relationships between objects, generate plans, and determine actions to reproduce a real-world demonstration. The networks are trained entirely in simulation, and the system is tested in the real world on the pick-and-place problem of stacking colored cubes using a Baxter robot.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
