This article proposes a novel learning-based control policy with strong generalizability to new environments that enables a mobile robot to navigate autonomously through spaces filled with both static obstacles and de...
详细信息
This article proposes a novel learning-based control policy with strong generalizability to new environments that enables a mobile robot to navigate autonomously through spaces filled with both static obstacles and dense crowds of pedestrians. The policy uses a unique combination of input data to generate the desired steering angle and forward velocity: a short history of lidar data, kinematic data about nearby pedestrians, and a subgoal point. The policy is trained in a reinforcement learning setting using a reward function that contains a novel term based on velocity obstacles to guide the robot to actively avoid pedestrians and move toward the goal. Through a series of 3-D simulated experiments with up to 55 pedestrians, this control policy is able to achieve a better balance between collision avoidance and speed (i.e., higher success rate and faster average speed) than state-of-the-art model-based and learning-based policies, and it also generalizes better to different crowd sizes and unseen environments. An extensive series of hardware experiments demonstrate the ability of this policy to directly work in different real-world environments with different crowd sizes with zero retraining. Furthermore, a series of simulated and hardware experiments show that the control policy also works in highly constrained static environments on a different robot platform without any additional training. Lastly, several important lessons that can be applied to other robot learning systems are summarized.
Robots working in unstructured environments must be capable of sensing and interpreting their surroundings. One of the main obstacles of deep-learning-based models in the field of robotics is the lack of domain-specif...
详细信息
Robots working in unstructured environments must be capable of sensing and interpreting their surroundings. One of the main obstacles of deep-learning-based models in the field of robotics is the lack of domain-specific labeled data for different industrial applications. In this article, we propose a sim2real transfer learning method based on domain randomization for object detection with which labeled synthetic datasets of arbitrary size and object types can be automatically generated. Subsequently, a state-of-the-art convolutional neural network, YOLOv4, is trained to detect the different types of industrial objects. With the proposed domain randomization method, we could shrink the reality gap to a satisfactory level, achieving 86.32% and 97.38% mAP(50) scores, respectively, in the case of zero-shot and one-shot transfers, on our manually annotated dataset containing 190 real images. Our solution fits for industrial use as the data generation process takes less than 0.5 s per image and the training lasts only around 12 h, on a GeForce RTX 2080 Ti GPU. Furthermore, it can reliably differentiate similar classes of objects by having access to only one real image for training. To our best knowledge, this is the only work thus far satisfying these constraints.
learning-enabled control systems have demonstrated impressive empirical performance on challenging control problems in robotics, but this performance comes at the cost of reduced transparency and lack of guarantees on...
详细信息
learning-enabled control systems have demonstrated impressive empirical performance on challenging control problems in robotics, but this performance comes at the cost of reduced transparency and lack of guarantees on the safety or stability of the learned controllers. In recent years, new techniques have emerged to provide these guarantees by learning certificates alongside control policies-these certificates provide concise data-driven proofs that guarantee the safety and stability of the learned control system. These methods not only allow the user to verify the safety of a learned controller but also provide supervision during training, allowing safety and stability requirements to influence the training process itself. In this article, we provide a comprehensive survey of this rapidly developing field of certificate learning. We hope that this article will serve as an accessible introduction to the theory and practice of certificate learning, both to those who wish to apply these tools to practical robotics problems and to those who wish to dive more deeply into the theory of learning for control.
In this article, a six-step approach is proposed to simu-late the grasp and evaluate the grasp quality for a versatile vacuum gripper by tracking the deformation and force-torque wrench of the gripping pad. Over 100 K...
详细信息
In this article, a six-step approach is proposed to simu-late the grasp and evaluate the grasp quality for a versatile vacuum gripper by tracking the deformation and force-torque wrench of the gripping pad. Over 100 K synthetic grasps are generated for neural network training. Furthermore, a gripping attention convolutional neural network (GA-CNN) is developed to predict the grasp quality for real-world grasp, running by 15 Hz closed-loop control with the real-time robotic observation and force-torque feedback. Various experiments in both the simulation and physical grasps indicate that our GA-CNN can focus on the crucial region of the soft gripping pad to predict grasp qualities and perform a lower average error compared with a same-scale traditional CNN. In addition, the complexity of grasping clutters is defined from Level 1 to Level 9. The proposed grasping method achieves an average success rate of 90.2% for static clutters at Level 1 to Level 8 and an average success rate of > 80.0% for dynamic grasping at Level 1 to Level 7, which outperforms state-of-the-art grasping methods.
Grasping is the process of picking up an object by applying forces and torques at a set of contacts. Recent advances in deeplearning methods have allowed rapid progress in robotic object grasping. In this systematic ...
详细信息
Grasping is the process of picking up an object by applying forces and torques at a set of contacts. Recent advances in deeplearning methods have allowed rapid progress in robotic object grasping. In this systematic review, we surveyed the publications over the last decade, with a particular interest in grasping an object using all six degrees of freedom of the end-effector pose. Our review found four common methodologies for robotic grasping: sampling-based approaches, direct regression, reinforcement learning, and exemplar approaches In addition, we found two "supporting methods" around grasping that use deeplearning to support the grasping process, shape approximation, and affordances. We have distilled the publications found in this systematic review (85 papers) into ten key takeaways we consider crucial for future robotic grasping and manipulation research.
Simulators perform an important role in prototyping, debugging, and benchmarking new advances in robotics and learning for control. Although many physics engines exist, some aspects of the real world are harder than o...
详细信息
Simulators perform an important role in prototyping, debugging, and benchmarking new advances in robotics and learning for control. Although many physics engines exist, some aspects of the real world are harder than others to simulate. One of the aspects that have so far eluded accurate simulation is touch sensing. To address this gap, we present TACTO - a fast, flexible, and open-source simulator for vision-based tactile sensors. This simulator allows to render realistic high-resolution touch readings at hundreds of frames per second, and can be easily configured to simulate different vision-based tactile sensors, including DIGIT and OmniTact. In this letter, we detail the principles that drove the implementation of TACTO and how they are reflected in its architecture. We demonstrate TACTO on a perceptual task, by learning to predict grasp stability using touch from 1 million grasps, and on a marble manipulation control task. Moreover, we provide a proof-of-concept that TACTO can be successfully used for Sim2Real applications. We believe that TACTO is a step towards the widespread adoption of touch sensing in robotic applications, and to enable machine learning practitioners interested in multi-modal learning and control.
We present a unified model-based and data-driven approach for quadrupedal planning and control to achieve dynamic locomotion over uneven terrain. We utilize on-board proprioceptive and exteroceptive feedback to map se...
详细信息
We present a unified model-based and data-driven approach for quadrupedal planning and control to achieve dynamic locomotion over uneven terrain. We utilize on-board proprioceptive and exteroceptive feedback to map sensory information and desired base velocity commands into footstep plans using a reinforcement learning (RL) policy. This RL policy is trained in simulation over a wide range of procedurally generated terrains. When run online, the system tracks the generated footstep plans using a model-based motion controller. We evaluate the robustness of our method over a wide variety of complex terrains. It exhibits behaviors that prioritize stability over aggressive locomotion. Additionally, we introduce two ancillary RL policies for corrective whole-body motion tracking and recovery control. These policies account for changes in physical parameters and external perturbations. We train and evaluate our framework on a complex quadrupedal system, ANYmal version B, and demonstrate transferability to a larger and heavier robot, ANYmal C, without requiring retraining.
Constrained motion planning is a challenging field of research, aiming for computationally efficient methods that can find a collision-free path on the constraint manifolds between a given start and goal configuration...
详细信息
Constrained motion planning is a challenging field of research, aiming for computationally efficient methods that can find a collision-free path on the constraint manifolds between a given start and goal configuration. These planning problems come up surprisingly frequently, such as in robot manipulation for performing daily life assistive tasks. However, few solutions to constrained motion planning are available, and those that exist struggle with high computational time complexity in finding a path solution on the manifolds. To address this challenge, we present Constrained Motion Planning Networks X (CoMPNetX). It is a neural planning approach, comprising a conditional deep neural generator and discriminator with neural gradients-based fast projection operator. We also introduce neural task and scene representations conditioned on which the CoMPNetX generates implicit manifold configurations to turbo-charge any underlying classical planner such as sampling-based motion planning methods for quickly solving complex constrained planning tasks. We show that our method finds path solutions with high success rates and lower computation times than state-of-the-art traditional path-finding tools on various challenging scenarios.
Recent methods for reinforcement learning from images use auxiliary tasks to learn image features that are used by the agent's policy or Q-function. In particular, methods based on contrastive learning that induce...
详细信息
Recent methods for reinforcement learning from images use auxiliary tasks to learn image features that are used by the agent's policy or Q-function. In particular, methods based on contrastive learning that induce linearity of the latent dynamics or invariance to data augmentation have been shown to greatly improve the sample efficiency of the reinforcement learning algorithm and the generalizability of the learned embedding. We further argue, that explicitly improving Markovianity of the learned embedding is desirable and propose a self-supervised representation learning method which integrates contrastive learning with dynamic models to synergistically combine these three objectives: (1) We maximize the InfoNCE bound on the mutual information between the state- and action-embedding and the embedding of the next state to induce a linearly predictive embedding without explicitly learning a linear transition model, (2) we further improve Markovianity of the learned embedding by explicitly learning a non-linear transition model using regression, and (3) we maximize the mutual information between the two nonlinear predictions of the next embeddings based on the current action and two independent augmentations of the current state, which naturally induces transformation invariance not only for the state embedding, but also for the nonlinear transition model. Experimental evaluation on the deepmind control suite shows that our proposed method achieves higher sample efficiency and better generalization than state-of-art methods based on contrastive learning or reconstruction. (c) 2021 Elsevier B.V. All rights reserved.
Intelligent warehouse based on the multi-robot system significantly improves logistics efficiency. Completing orders usually includes order task assignment and multi-robot path planning. These two processes influence ...
详细信息
ISBN:
(纸本)9798350334722
Intelligent warehouse based on the multi-robot system significantly improves logistics efficiency. Completing orders usually includes order task assignment and multi-robot path planning. These two processes influence each other. This paper presents a hierarchical task assignment and pathfinding (TAPF) solver, HGLP, for an intelligent warehouse. The high level is genetic algorithm based task assignment, and the lower level is the learning-based multi-agent pathfinding (MAPF) using reinforce to learn the policy. We tested our solver on warehouse-like structured maps of different sizes. The results show that: 1) Our MAPF solver significantly surpasses PRIMAL. 2) HGLP is much faster than the optimal TAPF solver CBS-TA. The difference between the minimum sum-of-cost (SOC) of HGLP and the value of CBS-TA is less than 2%.
暂无评论