arXiv subjects

Takamitsu Matsubara

Publications and source records attributed to Takamitsu Matsubara.

At least 55 records · Page 3Linked to original sources

arXiv2024

Task-priority Intermediated Hierarchical Distributed Policies: Reinforcement Learning of Adaptive Multi-robot Cooperative Transport

Multi-robot cooperative transport is crucial in logistics, housekeeping, and disaster response. However, it poses significant challenges in environments where objects of various weights are mixed and the number of robots and objects varies. This paper presents Task-priority Intermediated Hierarchical Distributed Policies (TIHDP), a multi-agent Reinforcement Learning (RL) framework that addresses these challenges through a hierarchical policy structure. TIHDP consists of three layers: task allocation policy (higher layer), dynamic task priority (intermediate layer), and robot control policy (lower layer). Whereas the dynamic task priority layer can manipulate the priority of any object to be transported by receiving global object information and communicating with other robots, the task allocation and robot control policies are restricted by local observations/actions so that they are not affected by changes in the number of objects and robots. Through simulations and real-robot demonstrations, TIHDP shows promising adaptability and performance of the learned multi-robot cooperative transport, even in environments with varying numbers of robots and objects. Video is available at https://youtu.be/Rmhv5ovj0xM

cs.RO↗

arXiv2024

Leveraging Demonstrator-perceived Precision for Safe Interactive Imitation Learning of Clearance-limited Tasks

Interactive imitation learning is an efficient, model-free method through which a robot can learn a task by repetitively iterating an execution of a learning policy and a data collection by querying human demonstrations. However, deploying unmatured policies for clearance-limited tasks, like industrial insertion, poses significant collision risks. For such tasks, a robot should detect the collision risks and request intervention by ceding control to a human when collisions are imminent. The former requires an accurate model of the environment, a need that significantly limits the scope of IIL applications. In contrast, humans implicitly demonstrate environmental precision by adjusting their behavior to avoid collisions when performing tasks. Inspired by human behavior, this paper presents a novel interactive learning method that uses demonstrator-perceived precision as a criterion for human intervention called Demonstrator-perceived Precision-aware Interactive Imitation Learning (DPIIL). DPIIL captures precision by observing the speed-accuracy trade-off exhibited in human demonstrations and cedes control to a human to avoid collisions in states where high precision is estimated. DPIIL improves the safety of interactive policy learning and ensures efficiency without explicitly providing precise information of the environment. We assessed DPIIL's effectiveness through simulations and real-robot experiments that trained a UR5e 6-DOF robotic arm to perform assembly tasks. Our results significantly improved training safety, and our best performance compared favorably with other learning methods.

cs.RO↗

arXiv2024

Incipient Slip Detection by Vibration Injection into Soft Sensor

In robotic manipulation, preventing objects from slipping and establishing a secure grip on them is critical. Successful manipulation requires tactile sensors that detect the microscopic incipient slip phenomenon at the contact surface. Unfortunately, the tiny signals generated by incipient slip are quickly buried by environmental noise, and precise stress-distribution measurement requires an extensive optical system and integrated circuits. In this study, we focus on the macroscopic deformation of the entire fingertip's soft structure instead of directly observing the contact surface and its role as a vibration medium for sensing. The proposed method compresses the stick ratio's information into a one-dimensional pressure signal using the change in the propagation characteristics by vibration injection into the soft structure, which magnifies the microscopic incipient slip phenomena into the entire deformation. This mechanism allows a tactile sensor to use just a single vibration sensor. In the implemented system, a biomimetic tactile sensor is vibrated using a white signal from a PZT motor and utilizes frequency spectrum change of the propagated vibration as features. We investigated the proposed method's effectiveness on stick-ratio estimation and \red{stick-ratio stabilization} control during incipient slip. Our estimation error and the control performance results significantly outperformed the conventional methods.

cs.RO↗

arXiv2023

Reinforcement Learning of Action and Query Policies with LTL Instructions under Uncertain Event Detector

Reinforcement learning (RL) with linear temporal logic (LTL) objectives can allow robots to carry out symbolic event plans in unknown environments. Most existing methods assume that the event detector can accurately map environmental states to symbolic events; however, uncertainty is inevitable for real-world event detectors. Such uncertainty in an event detector generates multiple branching possibilities on LTL instructions, confusing action decisions. Moreover, the queries to the uncertain event detector, necessary for the task's progress, may increase the uncertainty further. To cope with those issues, we propose an RL framework, Learning Action and Query over Belief LTL (LAQBL), to learn an agent that can consider the diversity of LTL instructions due to uncertain event detection while avoiding task failure due to the unnecessary event-detection query. Our framework simultaneously learns 1) an embedding of belief LTL, which is multiple branching possibilities on LTL instructions using a graph neural network, 2) an action policy, and 3) a query policy which decides whether or not to query for the event detector. Simulations in a 2D grid world and image-input robotic inspection environments show that our method successfully learns actions to follow LTL instructions even with uncertain event detectors.

cs.RO↗

arXiv2023

Deep Segmented DMP Networks for Learning Discontinuous Motions

Discontinuous motion which is a motion composed of multiple continuous motions with sudden change in direction or velocity in between, can be seen in state-aware robotic tasks. Such robotic tasks are often coordinated with sensor information such as image. In recent years, Dynamic Movement Primitives (DMP) which is a method for generating motor behaviors suitable for robotics has garnered several deep learning based improvements to allow associations between sensor information and DMP parameters. While the implementation of deep learning framework does improve upon DMP's inability to directly associate to an input, we found that it has difficulty learning DMP parameters for complex motion which requires large number of basis functions to reconstruct. In this paper we propose a novel deep learning network architecture called Deep Segmented DMP Network (DSDNet) which generates variable-length segmented motion by utilizing the combination of multiple DMP parameters predicting network architecture, double-stage decoder network, and number of segments predictor. The proposed method is evaluated on both artificial data (object cutting & pick-and-place) and real data (object cutting) where our proposed method could achieve high generalization capability, task-achievement, and data-efficiency compared to previous method on generating discontinuous long-horizon motions.

cs.RO↗

arXiv2023

AdaTerm: Adaptive T-Distribution Estimated Robust Moments for Noise-Robust Stochastic Gradient Optimization

With the increasing practicality of deep learning applications, practitioners are inevitably faced with datasets corrupted by noise from various sources such as measurement errors, mislabeling, and estimated surrogate inputs/outputs that can adversely impact the optimization results. It is a common practice to improve the optimization algorithm's robustness to noise, since this algorithm is ultimately in charge of updating the network parameters. Previous studies revealed that the first-order moment used in Adam-like stochastic gradient descent optimizers can be modified based on the Student's t-distribution. While this modification led to noise-resistant updates, the other associated statistics remained unchanged, resulting in inconsistencies in the assumed models. In this paper, we propose AdaTerm, a novel approach that incorporates the Student's t-distribution to derive not only the first-order moment but also all the associated statistics. This provides a unified treatment of the optimization process, offering a comprehensive framework under the statistical model of the t-distribution for the first time. The proposed approach offers several advantages over previously proposed approaches, including reduced hyperparameters and improved robustness and adaptability. This noise-adaptive behavior contributes to AdaTerm's exceptional learning performance, as demonstrated through various optimization problems with different and/or unknown noise ratios. Furthermore, we introduce a new technique for deriving a theoretical regret bound without relying on AMSGrad, providing a valuable contribution to the field

cs.LG↗

arXiv2023

Learning to Shape by Grinding: Cutting-surface-aware Model-based Reinforcement Learning

Object shaping by grinding is a crucial industrial process in which a rotating grinding belt removes material. Object-shape transition models are essential to achieving automation by robots; however, learning such a complex model that depends on process conditions is challenging because it requires a significant amount of data, and the irreversible nature of the removal process makes data collection expensive. This paper proposes a cutting-surface-aware Model-Based Reinforcement Learning (MBRL) method for robotic grinding. Our method employs a cutting-surface-aware model as the object's shape transition model, which in turn is composed of a geometric cutting model and a cutting-surface-deviation model, based on the assumption that the robot action can specify the cutting surface made by the tool. Furthermore, according to the grinding resistance theory, the cutting-surface-deviation model does not require raw shape information, making the model's dimensions smaller and easier to learn than a naive shape transition model directly mapping the shapes. Through evaluation and comparison by simulation and real robot experiments, we confirm that our MBRL method can achieve high data efficiency for learning object shaping by grinding and also provide generalization capability for initial and target shapes that differ from the training data.

cs.RO↗

arXiv2023

Cyclic Policy Distillation: Sample-Efficient Sim-to-Real Reinforcement Learning with Domain Randomization

Deep reinforcement learning with domain randomization learns a control policy in various simulations with randomized physical and sensor model parameters to become transferable to the real world in a zero-shot setting. However, a huge number of samples are often required to learn an effective policy when the range of randomized parameters is extensive due to the instability of policy updates. To alleviate this problem, we propose a sample-efficient method named cyclic policy distillation (CPD). CPD divides the range of randomized parameters into several small sub-domains and assigns a local policy to each one. Then local policies are learned while cyclically transitioning to sub-domains. CPD accelerates learning through knowledge transfer based on expected performance improvements. Finally, all of the learned local policies are distilled into a global policy for sim-to-real transfers. CPD's effectiveness and sample efficiency are demonstrated through simulations with four tasks (Pendulum from OpenAIGym and Pusher, Swimmer, and HalfCheetah from Mujoco), and a real-robot, ball-dispersal task. We published code and videos from our experiments at https://github.com/yuki-kadokawa/cyclic-policy-distillation.

cs.RO↗

arXiv2023

Disturbance Injection under Partial Automation: Robust Imitation Learning for Long-horizon Tasks

Partial Automation (PA) with intelligent support systems has been introduced in industrial machinery and advanced automobiles to reduce the burden of long hours of human operation. Under PA, operators perform manual operations (providing actions) and operations that switch to automatic/manual mode (mode-switching). Since PA reduces the total duration of manual operation, these two action and mode-switching operations can be replicated by imitation learning with high sample efficiency. To this end, this paper proposes Disturbance Injection under Partial Automation (DIPA) as a novel imitation learning framework. In DIPA, mode and actions (in the manual mode) are assumed to be observables in each state and are used to learn both action and mode-switching policies. The above learning is robustified by injecting disturbances into the operator's actions to optimize the disturbance's level for minimizing the covariate shift under PA. We experimentally validated the effectiveness of our method for long-horizon tasks in two simulations and a real robot environment and confirmed that our method outperformed the previous methods and reduced the demonstration burden.

cs.RO↗

arXiv2022

Learning Locally, Communicating Globally: Reinforcement Learning of Multi-robot Task Allocation for Cooperative Transport

We consider task allocation for multi-object transport using a multi-robot system, in which each robot selects one object among multiple objects with different and unknown weights. The existing centralized methods assume the number of robots and tasks to be fixed, which is inapplicable to scenarios that differ from the learning environment. Meanwhile, the existing distributed methods limit the minimum number of robots and tasks to a constant value, making them applicable to various numbers of robots and tasks. However, they cannot transport an object whose weight exceeds the load capacity of robots observing the object. To make it applicable to various numbers of robots and objects with different and unknown weights, we propose a framework using multi-agent reinforcement learning for task allocation. First, we introduce a structured policy model consisting of 1) predesigned dynamic task priorities with global communication and 2) a neural network-based distributed policy model that determines the timing for coordination. The distributed policy builds consensus on the high-priority object under local observations and selects cooperative or independent actions. Then, the policy is optimized by multi-agent reinforcement learning through trial and error. This structured policy of local learning and global communication makes our framework applicable to various numbers of robots and objects with different and unknown weights, as demonstrated by numerical simulations.

cs.RO↗

arXiv2022

Deep reinforcement learning of event-triggered communication and consensus-based control for distributed cooperative transport

In this paper, we present a solution to a design problem of control strategies for multi-agent cooperative transport. Although existing learning-based methods assume that the number of agents is the same as that in the training environment, the number might differ in reality considering that the robots' batteries may completely discharge, or additional robots may be introduced to reduce the time required to complete a task. Therefore, it is crucial that the learned strategy be applicable to scenarios wherein the number of agents differs from that in the training environment. In this paper, we propose a novel multi-agent reinforcement learning framework of event-triggered communication and consensus-based control for distributed cooperative transport. The proposed policy model estimates the resultant force and torque in a consensus manner using the estimates of the resultant force and torque with the neighborhood agents. Moreover, it computes the control and communication inputs to determine when to communicate with the neighboring agents under local observations and estimates of the resultant force and torque. Therefore, the proposed framework can balance the control performance and communication savings in scenarios wherein the number of agents differs from that in the training environment. We confirm the effectiveness of our approach by using a maximum of eight and six robots in the simulations and experiments, respectively.

cs.RO↗

arXiv2022

Bayesian Disturbance Injection: Robust Imitation Learning of Flexible Policies for Robot Manipulation

Humans demonstrate a variety of interesting behavioral characteristics when performing tasks, such as selecting between seemingly equivalent optimal actions, performing recovery actions when deviating from the optimal trajectory, or moderating actions in response to sensed risks. However, imitation learning, which attempts to teach robots to perform these same tasks from observations of human demonstrations, often fails to capture such behavior. Specifically, commonly used learning algorithms embody inherent contradictions between the learning assumptions (e.g., single optimal action) and actual human behavior (e.g., multiple optimal actions), thereby limiting robot generalizability, applicability, and demonstration feasibility. To address this, this paper proposes designing imitation learning algorithms with a focus on utilizing human behavioral characteristics, thereby embodying principles for capturing and exploiting actual demonstrator behavioral characteristics. This paper presents the first imitation learning framework, Bayesian Disturbance Injection (BDI), that typifies human behavioral characteristics by incorporating model flexibility, robustification, and risk sensitivity. Bayesian inference is used to learn flexible non-parametric multi-action policies, while simultaneously robustifying policies by injecting risk-sensitive disturbances to induce human recovery action and ensuring demonstration feasibility. Our method is evaluated through risk-sensitive simulations and real-robot experiments (e.g., table-sweep task, shaft-reach task and shaft-insertion task) using the UR5e 6-DOF robotic arm, to demonstrate the improved characterisation of behavior. Results show significant improvement in task performance, through improved flexibility, robustness as well as demonstration feasibility.

cs.RO↗

arXiv2022

Bayesian Disturbance Injection: Robust Imitation Learning of Flexible Policies

Scenarios requiring humans to choose from multiple seemingly optimal actions are commonplace, however standard imitation learning often fails to capture this behavior. Instead, an over-reliance on replicating expert actions induces inflexible and unstable policies, leading to poor generalizability in an application. To address the problem, this paper presents the first imitation learning framework that incorporates Bayesian variational inference for learning flexible non-parametric multi-action policies, while simultaneously robustifying the policies against sources of error, by introducing and optimizing disturbances to create a richer demonstration dataset. This combinatorial approach forces the policy to adapt to challenging situations, enabling stable multi-action policies to be learned efficiently. The effectiveness of our proposed method is evaluated through simulations and real-robot experiments for a table-sweep task using the UR3 6-DOF robotic arm. Results show that, through improved flexibility and robustness, the learning performance and control safety are better than comparison methods.

cs.RO↗

arXiv2022

Deep Koopman with Control: Spectral Analysis of Soft Robot Dynamics

Soft robots are challenging to model and control as inherent non-linearities (e.g., elasticity and deformation), often requires complex explicit physics-based analytical modeling (e.g., a priori geometric definitions). While machine learning can be used to learn non-linear control models in a data-driven approach, these models often lack an intuitive internal physical interpretation and representation, limiting dynamical analysis. To address this, this paper presents an approach using Koopman operator theory and deep neural networks to provide a global linear description of the non-linear control systems. Specifically, by globally linearising dynamics, the Koopman operator is analyzed using spectral decomposition to characterises important physics-based interpretations, such as functional growths and oscillations. Experiments in this paper demonstrate this approach for controlling non-linear soft robotics, and shows model outputs are interpretable in the context of spectral analysis.

cs.RO↗

arXiv2022

Goal-Aware Generative Adversarial Imitation Learning from Imperfect Demonstration for Robotic Cloth Manipulation

Generative Adversarial Imitation Learning (GAIL) can learn policies without explicitly defining the reward function from demonstrations. GAIL has the potential to learn policies with high-dimensional observations as input, e.g., images. By applying GAIL to a real robot, perhaps robot policies can be obtained for daily activities like washing, folding clothes, cooking, and cleaning. However, human demonstration data are often imperfect due to mistakes, which degrade the performance of the resulting policies. We address this issue by focusing on the following features: 1) many robotic tasks are goal-reaching tasks, and 2) labeling such goal states in demonstration data is relatively easy. With these in mind, this paper proposes Goal-Aware Generative Adversarial Imitation Learning (GA-GAIL), which trains a policy by introducing a second discriminator to distinguish the goal state in parallel with the first discriminator that indicates the demonstration data. This extends a standard GAIL framework to more robustly learn desirable policies even from imperfect demonstrations through a goal-state discriminator that promotes achieving the goal state. Furthermore, GA-GAIL employs the Entropy-maximizing Deep P-Network (EDPN) as a generator, which considers both the smoothness and causal entropy in the policy update, to achieve stable policy learning from two discriminators. Our proposed method was successfully applied to two real-robotic cloth-manipulation tasks: turning a handkerchief over and folding clothes. We confirmed that it learns cloth-manipulation policies without task-specific reward function design. Video of the real experiments are available at https://youtu.be/h_nII2ooUrE.

cs.RO↗

arXiv2022

Physically Consistent Preferential Bayesian Optimization for Food Arrangement

This paper considers the problem of estimating a preferred food arrangement for users from interactive pairwise comparisons using Computer Graphics (CG)-based dish images. As a foodservice industry requirement, we need to utilize domain rules for the geometry of the arrangement (e.g., the food layout of some Japanese dishes is reminiscent of mountains). However, those rules are qualitative and ambiguous; the estimated result might be physically inconsistent (e.g., each food physically interferes, and the arrangement becomes infeasible). To cope with this problem, we propose Physically Consistent Preferential Bayesian Optimization (PCPBO) as a method that obtains physically feasible and preferred arrangements that satisfy domain rules. PCPBO employs a bi-level optimization that combines a physical simulation-based optimization and a Preference-based Bayesian Optimization (PbBO). Our experimental results demonstrated the effectiveness of PCPBO on simulated and actual human users.

eess.SY↗

arXiv2022

Randomized-to-Canonical Model Predictive Control for Real-world Visual Robotic Manipulation

Many works have recently explored Sim-to-real transferable visual model predictive control (MPC). However, such works are limited to one-shot transfer, where real-world data must be collected once to perform the sim-to-real transfer, which remains a significant human effort in transferring the models learned in simulations to new domains in the real world. To alleviate this problem, we first propose a novel model-learning framework called Kalman Randomized-to-Canonical Model (KRC-model). This framework is capable of extracting task-relevant intrinsic features and their dynamics from randomized images. We then propose Kalman Randomized-to-Canonical Model Predictive Control (KRC-MPC) as a zero-shot sim-to-real transferable visual MPC using KRC-model. The effectiveness of our method is evaluated through a valve rotation task by a robot hand in both simulation and the real world, and a block mating task in simulation. The experimental results show that KRC-MPC can be applied to various real domains and tasks in a zero-shot manner.

cs.RO↗

arXiv2022

$q$-Munchausen Reinforcement Learning

The recently successful Munchausen Reinforcement Learning (M-RL) features implicit Kullback-Leibler (KL) regularization by augmenting the reward function with logarithm of the current stochastic policy. Though significant improvement has been shown with the Boltzmann softmax policy, when the Tsallis sparsemax policy is considered, the augmentation leads to a flat learning curve for almost every problem considered. We show that it is due to the mismatch between the conventional logarithm and the non-logarithmic (generalized) nature of Tsallis entropy. Drawing inspiration from the Tsallis statistics literature, we propose to correct the mismatch of M-RL with the help of $q$-logarithm/exponential functions. The proposed formulation leads to implicit Tsallis KL regularization under the maximum Tsallis entropy framework. We show such formulation of M-RL again achieves superior performance on benchmark problems and sheds light on more general M-RL with various entropic indices $q$.

cs.LG↗