Learning Robust Bed Making using Deep Imitation Learning with DART
نویسندگان
چکیده
Bed-making is a universal home task that can be challenging for senior citizens due to reaching motions. Automating bed-making has multiple technical challenges such as perception in an unstructured environments, deformable object manipulation, obstacle avoidance and sequential decision making. We explore how DART, an LfD algorithm for learning robust policies, can be applied to automating bed making without fiducial markers with a Toyota Human Support Robot (HSR). By gathering human demonstrations for grasping the sheet and failure detection, we can learn deep neural network policies that leverage pre-trained YOLO features to automate the task. Experiments with a scale bed and distractors placed on the bed, suggest policies learned on 50 demonstrations with DART achieve 96% sheet coverage, which is over 200% better than a corner detector baseline using contour detection.
منابع مشابه
DART: Noise Injection for Robust Imitation Learning
One approach to Imitation Learning is Behavior Cloning, in which a robot observes a supervisor and infers a control policy. A known problem with this “off-policy” approach is that the robot’s errors compound when drifting away from the supervisor’s demonstrations. On-policy, techniques alleviate this by iteratively collecting corrective actions for the current robot policy. However, these techn...
متن کاملDeep Imitation Learning for Parameterized Action Spaces
Recent results have demonstrated the ability of deep neural networks to serve as effective controllers (or function approximators of the value function) for complex sequential decision-making tasks, including those with raw visual inputs. However, to the best of our knowledge, such demonstrations have been limited to tasks either fully discrete or fully continuous actions. This paper introduces...
متن کاملRobust Imitation of Diverse Behaviors
Deep generative models have recently shown great promise in imitation learning for motor control. Given enough data, even supervised approaches can do one-shot imitation learning; however, they are vulnerable to cascading failures when the agent trajectory diverges from the demonstrations. Compared to purely supervised methods, Generative Adversarial Imitation Learning (GAIL) can learn more rob...
متن کاملEffect Feedback after Good and Poor Trials on learning and Error Detection Ability Children in Dart Throwing Skill
Augmented feedback is information that guidance performance to direction correct response and has critical role in motor skill learning. The purpose of this study was to examine the effect of knowledge of results, after good and poor trials on learning and error estimation capability in children.32 elementary students (Mean age 10/4, SD ± 0/9) that all novice and no experience in dart skill par...
متن کاملComparison Effect of Quiet Eye and Quiet Mind Training on learning of Dart Throws Skill
The aim of present study is to investigate effect of the quiet eye and quiet mind training on the dart throw learning. Thirty young males were selected with 24.53 mean aged through convenience sampling and randomly divided into quiet eye group, quiet mind group and control group. The study was conducted in four phases, including: Pre-test, training in quiet eye and quiet mind training, retentio...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1711.02525 شماره
صفحات -
تاریخ انتشار 2017