skip to main content

Title: Pixel-Attentive Policy Gradient for Multi-Fingered Grasping in Cluttered Scenes
Recent advances in on-policy reinforcement learning (RL) methods enabled learning agents in virtual environments to master complex tasks with high-dimensional and continuous observation and action spaces. However, leveraging this family of algorithms in multi-fingered robotic grasping remains a challenge due to large sim-to-real fidelity gaps and the high sample complexity of on-policy RL algorithms. This work aims to bridge these gaps by first reinforcement-learning a multi-fingered robotic grasping policy in simulation that operates in the pixel space of the input: a single depth image. Using a mapping from pixel space to Cartesian space according to the depth map, this method transfers to the real world with high fidelity and introduces a novel attention mechanism that substantially improves grasp success rate in cluttered environments. Finally, the direct-generative nature of this method allows learning of multi-fingered grasps that have flexible end-effector positions, orientations and rotations, as well as all degrees of freedom of the hand.
Authors:
; ;
Award ID(s):
1734557
Publication Date:
NSF-PAR ID:
10164439
Journal Name:
2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Page Range or eLocation-ID:
1789 to 1796
Sponsoring Org:
National Science Foundation
More Like this
  1. Generative Attention Learning (GenerAL) is a framework for high-DOF multi-fingered grasping that is not only robust to dense clutter and novel objects but also effective with a variety of different parallel-jaw and multi-fingered robot hands. This framework introduces a novel attention mechanism that substantially improves the grasp success rate in clutter. Its generative nature allows the learning of full-DOF grasps with flexible end-effector positions and orientations, as well as all finger joint angles of the hand. Trained purely in simulation, this framework skillfully closes the sim-to-real gap. To close the visual sim-to-real gap, this framework uses a single depth imagemore »as input. To close the dynamics sim-to-real gap, this framework circumvents continuous motor control with a direct mapping from pixel to Cartesian space inferred from the same depth image. Finally, this framework demonstrates inter-robot generality by achieving over 92% real-world grasp success rates in cluttered scenes with novel objects using two multi-fingered robotic hand-arm systems with different degrees of freedom.« less
  2. There has been significant recent work on data-driven algorithms for learning general-purpose grasping policies. However, these policies can consis- tently fail to grasp challenging objects which are significantly out of the distribution of objects in the training data or which have very few high quality grasps. Moti- vated by such objects, we propose a novel problem setting, Exploratory Grasping, for efficiently discovering reliable grasps on an unknown polyhedral object via sequential grasping, releasing, and toppling. We formalize Exploratory Grasping as a Markov Decision Process where we assume that the robot can (1) distinguish stable poses of a polyhedral object ofmore »unknown geometry, (2) generate grasp can- didates on these poses and execute them, (3) determine whether each grasp is successful, and (4) release the object into a random new pose after a grasp success or topple the object after a grasp failure. We study the theoretical complexity of Exploratory Grasping in the context of reinforcement learning and present an efficient bandit-style algorithm, Bandits for Online Rapid Grasp Exploration Strategy (BORGES), which leverages the structure of the problem to efficiently discover high performing grasps for each object stable pose. BORGES can be used to complement any general-purpose grasping algorithm with any grasp modality (parallel-jaw, suction, multi-fingered, etc) to learn policies for objects in which they exhibit persistent failures. Simulation experiments suggest that BORGES can significantly outperform both general-purpose grasping pipelines and two other online learning algorithms and achieves performance within 5% of the optimal policy within 1000 and 8000 timesteps on average across 46 challenging objects from the Dex-Net adversarial and EGAD! object datasets, respectively. Initial physical experiments suggest that BORGES can improve grasp success rate by 45% over a Dex-Net baseline with just 200 grasp attempts in the real world. See https://tinyurl.com/exp-grasping for supplementary material and videos.« less
  3. Our goal is to learn control policies for robots that provably generalize well to novel environments given a dataset of example environments. The key technical idea behind our approach is to leverage tools from generalization theory in machine learning by exploiting a precise analogy (which we present in the form of a reduction) between generalization of control policies to novel environments and generalization of hypotheses in the supervised learning setting. In particular, we utilize the probably approximately correct (PAC)-Bayes framework, which allows us to obtain upper bounds that hold with high probability on the expected cost of (stochastic) control policiesmore »across novel environments. We propose policy learning algorithms that explicitly seek to minimize this upper bound. The corresponding optimization problem can be solved using convex optimization (relative entropy programming in particular) in the setting where we are optimizing over a finite policy space. In the more general setting of continuously parameterized policies (e.g., neural network policies), we minimize this upper bound using stochastic gradient descent. We present simulated results of our approach applied to learning (1) reactive obstacle avoidance policies and (2) neural network-based grasping policies. We also present hardware results for the Parrot Swing drone navigating through different obstacle environments. Our examples demonstrate the potential of our approach to provide strong generalization guarantees for robotic systems with continuous state and action spaces, complicated (e.g., nonlinear) dynamics, rich sensory inputs (e.g., depth images), and neural network-based policies.

    « less
  4. Aleksandra Faust, David Hsu (Ed.)
    Modern Reinforcement Learning (RL) algorithms are not sample efficient to train on multi-step tasks in complex domains, impeding their wider deployment in the real world. We address this problem by leveraging the insight that RL models trained to complete one set of tasks can be repurposed to complete related tasks when given just a handful of demonstrations. Based upon this insight, we propose See-SPOT-Run (SSR), a new computational approach to robot learning that enables a robot to complete a variety of real robot tasks in novel problem domains without task-specific training. SSR uses pretrained RL models to create vectors thatmore »represent model, task, and action relevance in demonstration and test scenes. SSR then compares these vectors via our Cycle Consistency Distance (CCD) metric to determine the next action to take. SSR completes 58% more task steps and 20% more trials than a baseline few-shot learning method that requires task-specific training. SSR also achieves a four order of magnitude improvement in compute efficiency and a 20% to three order of magnitude improvement in sample efficiency compared to the baseline and to training RL models from scratch. To our knowledge, we are the first to address multi-step tasks from demonstration on a real robot without task-specific training, where both the visual input and action space output are high dimensional. Code is available in the supplement.« less
  5. Off-policy deep reinforcement learning (RL) has been successful in a range of challenging domains. However, standard off-policy RL algorithms can suffer from several issues, such as instability in Qlearning and balancing exploration and exploitation. To mitigate these issues, we present SUNRISE, a simple unified ensemble method, which is compatible with various off-policy RL algorithms. SUNRISE integrates two key ingredients: (a) ensemble-based weighted Bellman backups, which re-weight target Q-values based on uncertainty estimates from a Q-ensemble, and (b) an inference method that selects actions using the highest upper-confidence bounds for efficient exploration. By enforcing the diversity between agents using Bootstrap withmore »random initialization, we show that these different ideas are largely orthogonal and can be fruitfully integrated, together further improving the performance of existing off-policy RL algorithms, such as Soft Actor-Critic and Rainbow DQN, for both continuous and discrete control tasks on both low-dimensional and high-dimensional environments.« less