اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدBehavior Self-Organization Supports Task Inference for Continual Robot Learning
126
0
0.0
(
0
)
نشر من قبل
Muhammad Burhan Hafez
تاريخ النشر
2021
مجال البحث
الهندسة المعلوماتية
والبحث باللغة
English
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Recent advances in robot learning have enabled robots to become increasingly better at mastering a predefined set of tasks. On the other hand, as humans, we have the ability to learn a growing set of tasks over our lifetime. Continual robot learning is an emerging research direction with the goal of endowing robots with this ability. In order to learn new tasks over time, the robot first needs to infer the task at hand. Task inference, however, has received little attention in the multi-task learning literature. In this paper, we propose a novel approach to continual learning of robotic control tasks. Our approach performs unsupervised learning of behavior embeddings by incrementally self-organizing demonstrated behaviors. Task inference is made by finding the nearest behavior embedding to a demonstrated behavior, which is used together with the environment state as input to a multi-task policy trained with reinforcement learning to optimize performance over tasks. Unlike previous approaches, our approach makes no assumptions about task distribution and requires no task exploration to infer tasks. We evaluate our approach in experiments with concurrently and sequentially presented tasks and show that it outperforms other multi-task learning approaches in terms of generalization performance and convergence speed, particularly in the continual learning setting.
قيم البحث
اقرأ أيضاً
In order to detect and correct physical exercises, a Grow-When-Required Network (GWR) with recurrent connections, episodic memory and a novel subnode mechanism is developed in order to learn spatiotemporal relationships of body movements and poses. O
nce an exercise is performed, the information of pose and movement per frame is stored in the GWR. For every frame, the current pose and motion pair is compared against a predicted output of the GWR, allowing for feedback not only on the pose but also on the velocity of the motion. In a practical scenario, a physical exercise is performed by an expert like a physiotherapist and then used as a reference for a humanoid robot like Pepper to give feedback on a patients execution of the same exercise. This approach, however, comes with two challenges. First, the distance from the humanoid robot and the position of the user in the cameras view of the humanoid robot have to be considered by the GWR as well, requiring a robustness against the users positioning in the field of view of the humanoid robot. Second, since both the pose and motion are dependent on the body measurements of the original performer, the experts exercise cannot be easily used as a reference. This paper tackles the first challenge by designing an architecture that allows for tolerances in translation and rotations regarding the center of the field of view. For the second challenge, we allow the GWR to grow online on incremental data. For evaluation, we created a novel exercise dataset with virtual avatars called the Virtual-Squat dataset. Overall, we claim that our novel architecture based on the GWR can use a learned exercise reference for different body variations through continual online learning, while preventing catastrophic forgetting, enabling for an engaging long-term human-robot interaction with a humanoid robot.
While neural networks are powerful function approximators, they suffer from catastrophic forgetting when the data distribution is not stationary. One particular formalism that studies learning under non-stationary distribution is provided by continua
l learning, where the non-stationarity is imposed by a sequence of distinct tasks. Most methods in this space assume, however, the knowledge of task boundaries, and focus on alleviating catastrophic forgetting. In this work, we depart from this view and move the focus towards faster remembering -- i.e measuring how quickly the network recovers performance rather than measuring the networks performance without any adaptation. We argue that in many settings this can be more effective and that it opens the door to combining meta-learning and continual learning techniques, leveraging their complementary advantages. We propose a framework specific for the scenario where no information about task boundaries or task identity is given. It relies on a separation of concerns into what task is being solved and how the task should be solved. This framework is implemented by differentiating task specific parameters from task agnostic parameters, where the latter are optimized in a continual meta learning fashion, without access to multiple tasks at the same time. We showcase this framework in a supervised learning scenario and discuss the implication of the proposed formalism.
Pouring is one of the most commonly executed tasks in humans daily lives, whose accuracy is affected by multiple factors, including the type of material to be poured and the geometry of the source and receiving containers. In this work, we propose a
self-supervised learning approach that learns the pouring dynamics, pouring motion, and outcomes from unsupervised demonstrations for accurate pouring. The learned pouring model is then generalized by self-supervised practicing to different conditions such as using unaccustomed pouring cups. We have evaluated the proposed approach first with one container from the training set and four new but similar containers. The proposed approach achieved better pouring accuracy than a regular human with a similar pouring speed for all five cups. Both the accuracy and pouring speed outperform state-of-the-art works. We have also evaluated the proposed self-supervised generalization approach using unaccustomed containers that are far different from the ones in the training set. The self-supervised generalization reduces the pouring error of the unaccustomed containers to the desired accuracy level.
We explore task-free continual learning (CL), in which a model is trained to avoid catastrophic forgetting, but without being provided any explicit task boundaries or identities. However, since CL models are continually updated, the utility of stored
seen examples may diminish over time. Here, we propose Gradient based Memory EDiting (GMED), a framework for editing stored examples in continuous input space via gradient updates, in order to create a wide range of more ``challenging examples for replay. GMED-edited examples remain similar to their unedited forms, but can yield increased loss in the upcoming model updates, thereby making the future replays more effective in overcoming catastrophic forgetting. By construction, GMED can be seamlessly applied in conjunction with other memory-based CL algorithms to bring further improvement. Experiments on six datasets validate that GMED is effective, and our single best method significantly outperforms existing approaches on three datasets. Code and data can be found at https://github.com/INK-USC/GMED.
A practical approach to robot reinforcement learning is to first collect a large batch of real or simulated robot interaction data, using some data collection policy, and then learn from this data to perform various tasks, using offline learning algo
rithms. Previous work focused on manually designing the data collection policy, and on tasks where suitable policies can easily be designed, such as random picking policies for collecting data about object grasping. For more complex tasks, however, it may be difficult to find a data collection policy that explores the environment effectively, and produces data that is diverse enough for the downstream task. In this work, we propose that data collection policies should actively explore the environment to collect diverse data. In particular, we develop a simple-yet-effective goal-conditioned reinforcement-learning method that actively focuses data collection on novel observations, thereby collecting a diverse data-set. We evaluate our method on simulated robot manipulation tasks with visual inputs and show that the improved diversity of active data collection leads to significant improvements in the downstream learning tasks.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
