اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدAccelerating Grasp Exploration by Leveraging Learned Priors
77
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
The ability of robots to grasp novel objects has industry applications in e-commerce order fulfillment and home service. Data-driven grasping policies have achieved success in learning general strategies for grasping arbitrary objects. However, these approaches can fail to grasp objects which have complex geometry or are significantly outside of the training distribution. We present a Thompson sampling algorithm that learns to grasp a given object with unknown geometry using online experience. The algorithm leverages learned priors from the Dexterity Network robot grasp planner to guide grasp exploration and provide probabilistic estimates of grasp success for each stable pose of the novel object. We find that seeding the policy with the Dex-Net prior allows it to more efficiently find robust grasps on these objects. Experiments suggest that the best learned policy attains an average total reward 64.5% higher than a greedy baseline and achieves within 5.7% of an oracle baseline when evaluated over 300,000 training runs across a set of 3000 object poses.
قيم البحث
اقرأ أيضاً
Intelligent agents rely heavily on prior experience when learning a new task, yet most modern reinforcement learning (RL) approaches learn every task from scratch. One approach for leveraging prior knowledge is to transfer skills learned on prior tas
ks to the new task. However, as the amount of prior experience increases, the number of transferable skills grows too, making it challenging to explore the full set of available skills during downstream learning. Yet, intuitively, not all skills should be explored with equal probability; for example information about the current state can hint which skills are promising to explore. In this work, we propose to implement this intuition by learning a prior over skills. We propose a deep latent variable model that jointly learns an embedding space of skills and the skill prior from offline agent experience. We then extend common maximum-entropy RL approaches to use skill priors to guide downstream learning. We validate our approach, SPiRL (Skill-Prior RL), on complex navigation and robotic manipulation tasks and show that learned skill priors are essential for effective skill transfer from rich datasets. Videos and code are available at https://clvrai.com/spirl.
In this paper, we introduce a Grasp Manifold Estimator (GraspME) to detect grasp affordances for objects directly in 2D camera images. To perform manipulation tasks autonomously it is crucial for robots to have such graspability models of the surroun
ding objects. Grasp manifolds have the advantage of providing continuously infinitely many grasps, which is not the case when using other grasp representations such as predefined grasp points. For instance, this property can be leveraged in motion optimization to define goal sets as implicit surface constraints in the robot configuration space. In this work, we restrict ourselves to the case of estimating possible end-effector positions directly from 2D camera images. To this extend, we define grasp manifolds via a set of key points and locate them in images using a Mask R-CNN backbone. Using learned features allows generalizing to different view angles, with potentially noisy images, and objects that were not part of the training set. We rely on simulation data only and perform experiments on simple and complex objects, including unseen ones. Our framework achieves an inference speed of 11.5 fps on a GPU, an average precision for keypoint estimation of 94.5% and a mean pixel distance of only 1.29. This shows that we can estimate the objects very well via bounding boxes and segmentation masks as well as approximate the correct grasp manifolds keypoint coordinates.
Manipulation in contrast to grasping is a trajectorial task that needs to use dexterous hands. Improving the dexterity of robot hands, increases the controller complexity and thus requires to use the concept of postural synergies. Inspired from postu
ral synergies, this research proposes a new framework called kernelized synergies that focuses on the re-usability of the same subspace for precision grasping and dexterous manipulation. In this work, the computed subspace of postural synergies; parameterized by probabilistic movement primitives, is treated with kernel to preserve its grasping and manipulation characteristics and allows its reuse for new objects. The grasp stability of the proposed framework is assessed with a force closure quality index. For performance evaluation, the proposed framework is tested on two different simulated robot hand models using the Syngrasp toolbox and experimentally, four complex grasping and manipulation tasks are performed and reported. The results confirm the hand agnostic approach of the proposed framework and its generalization to distinct objects irrespective of their shape and size.
Meta-learning algorithms can accelerate the model-based reinforcement learning (MBRL) algorithms by finding an initial set of parameters for the dynamical model such that the model can be trained to match the actual dynamics of the system with only a
few data-points. However, in the real world, a robot might encounter any situation starting from motor failures to finding itself in a rocky terrain where the dynamics of the robot can be significantly different from one another. In this paper, first, we show that when meta-training situations (the prior situations) have such diverse dynamics, using a single set of meta-trained parameters as a starting point still requires a large number of observations from the real system to learn a useful model of the dynamics. Second, we propose an algorithm called FAMLE that mitigates this limitation by meta-training several initial starting points (i.e., initial parameters) for training the model and allows the robot to select the most suitable starting point to adapt the model to the current situation with only a few gradient steps. We compare FAMLE to MBRL, MBRL with a meta-trained model with MAML, and model-free policy search algorithm PPO for various simulated and real robotic tasks, and show that FAMLE allows the robots to adapt to novel damages in significantly fewer time-steps than the baselines.
We describe a robotic learning system for autonomous exploration and navigation in diverse, open-world environments. At the core of our method is a learned latent variable model of distances and actions, along with a non-parametric topological memory
. We use an information bottleneck to regularize the learned policy, giving us (i) a compact visual representation of goals, (ii) improved generalization capabilities, and (iii) a mechanism for sampling feasible goals for exploration. Trained on a large offline dataset of prior experience, the model acquires a representation of visual goals that is robust to task-irrelevant distractors. We demonstrate our method on a mobile ground robot in open-world exploration scenarios. Given an image of a goal that is up to 80 meters away, our method leverages its representation to explore and discover the goal in under 20 minutes, even amidst previously-unseen obstacles and weather conditions. We encourage the reader to visit the project website for videos of our experiments and demonstrations https://sites.google.com/view/recon-robot
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
