Robot Deformable Object Manipulation via NMPC-generated Demonstrations in Deep Reinforcement Learning

In this work, we conducted research on deformable object manipulation by robots based on demonstration-enhanced reinforcement learning (RL). To improve the learning efficiency of RL, we enhanced the utilization of demonstration data from multiple aspects and proposed the HGCR-DDPG algorithm. It uses a novel high-dimensional fuzzy approach for grasping-point selection, a refined behavior-cloning method to enhance data-driven learning in Rainbow-DDPG, and a sequential policy-learning strategy. Compared to the baseline algorithm (Rainbow-DDPG), our proposed HGCR-DDPG achieved 2.01 times the global average reward and reduced the global average standard deviation to 45% of that of the baseline algorithm. To reduce the human labor cost of demonstration collection, we proposed a low-cost demonstration collection method based on Nonlinear Model Predictive Control (NMPC). Simulation experiment results show that demonstrations collected through NMPC can be used to train HGCR-DDPG, achieving comparable results to those obtained with human demonstrations. To validate the feasibility of our proposed methods in real-world environments, we conducted physical experiments involving deformable object manipulation. We manipulated fabric to perform three tasks: diagonal folding, central axis folding, and flattening. The experimental results demonstrate that our proposed method achieved success rates of 83.3%, 80%, and 100% for these three tasks, respectively, validating the effectiveness of our approach. Compared to current large-model approaches for robot manipulation, the proposed algorithm is lightweight, requires fewer computational resources, and offers task-specific customization and efficient adaptability for specific tasks.

Learning to Group and Grasp Multiple Objects

Simultaneously grasping and transporting multiple objects can significantly enhance robotic work efficiency and has been a key research focus for decades. The primary challenge lies in determining how to push objects, group them, and execute simultaneous grasping for respective groups while considering object distribution and the hardware constraints of the robot. Traditional rule-based methods struggle to flexibly adapt to diverse scenarios. To address this challenge, this paper proposes an imitation learning-based approach. We collect a series of expert demonstrations through teleoperation and train a diffusion policy network, enabling the robot to dynamically generate action sequences for pushing, grouping, and grasping, thereby facilitating efficient multi-object grasping and transportation. We conducted experiments to evaluate the method under different training dataset sizes, varying object quantities, and real-world object scenarios. The results demonstrate that the proposed approach can effectively and adaptively generate multi-object grouping and grasping strategies. With the support of more training data, imitation learning is expected to be an effective approach for solving the multi-object grasping problem.

Adaptive Grasping of Moving Objects in Dense Clutter via Global-to-Local Detection and Static-to-Dynamic Planning

Robotic grasping is facing a variety of real-world uncertainties caused by non-static object states, unknown object properties, and cluttered object arrangements. The difficulty of grasping increases with the presence of more uncertainties, where commonly used learning-based approaches struggle to perform consistently across varying conditions. In this study, we integrate the idea of similarity matching to tackle the challenge of grasping novel objects that are simultaneously in motion and densely cluttered using a single RGBD camera, where multiple uncertainties coexist. We achieve this by shifting visual detection from global to local states and operating grasp planning from static to dynamic scenes. Notably, we introduce optimization methods to enhance planning efficiency for this time-sensitive task. Our proposed system can adapt to various object types, arrangements and movement speeds without the need for extensive training, as demonstrated by real-world experiments.

Temperature Driven Multi-modal/Single-actuated Soft Finger

Soft pneumatic fingers are of great research interest. However, their significant potential is limited as most of them can generate only one motion, mostly bending. The conventional design of soft fingers does not allow them to switch to another motion mode. In this paper, we developed a novel multi-modal and single-actuated soft finger where its motion mode is switched by changing the finger's temperature. Our soft finger is capable of switching between three distinctive motion modes: bending, twisting, and extension-in approximately five seconds. We carried out a detailed experimental study of the soft finger and evaluated its repeatability and range of motion. It exhibited repeatability of around one millimeter and a fifty percent larger range of motion than a standard bending actuator. We developed an analytical model for a fiber-reinforced soft actuator for twisting motion. This helped us relate the input pressure to the output twist radius of the twisting motion. This model was validated by experimental verification. Further, a soft robotic gripper with multiple grasp modes was developed using three actuators. This gripper can adapt to and grasp objects of a large range of size, shape, and stiffness. We showcased its grasping capabilities by successfully grasping a small berry, a large roll, and a delicate tofu cube.

Task-Difficulty-Aware Efficient Object Arrangement Leveraging Tossing Motions

This study explores a pick-and-toss (PT) as an alternative to pick-and-place (PP), allowing a robot to extend its range and improve task efficiency. Although PT boosts efficiency in object arrangement, the placement environment critically affects the success of tossing. To achieve accurate and efficient object arrangement, we suggest choosing between PP and PT based on task difficulty estimated from the placement environment. Our method simultaneously learns the tossing motion through self-supervised learning and the task determination policy via brute-force search. Experimental results validate the proposed method through simulations and real-world tests on various rectangular object arrangements.

Direction-Constrained Control for Efficient Physical Human-Robot Interaction under Hierarchical Tasks

This paper proposes a control method to address the physical Human-Robot Interaction (pHRI) challenge in the context of hierarchical tasks. A common approach to managing hierarchical tasks is Hierarchical Quadratic Programming (HQP), which, however, cannot be directly applied to human interaction due to its allowance of arbitrary velocity direction adjustments. To resolve this limitation, we introduce the concept of directional constraints and develop a direction-constrained optimization algorithm to handle the nonlinearities induced by these constraints. The algorithm solves two sub-problems, minimizing the error and minimizing the deviation angle, in parallel, and combines the results of the two sub-problems to produce a final optimal outcome. The mutual influence between these two sub-problems is analyzed to determine the best parameter for combination. Additionally, the velocity objective in our control framework is computed using a variable admittance controller. Traditional admittance control does not account for constraints. To address this issue, we propose a variable admittance control method to adjust control objectives dynamically. The method helps reduce the deviation between robot velocity and human intention at the constraint boundaries, thereby enhancing interaction efficiency. We evaluate the proposed method in scenarios where a human operator physically interacts with a 7-degree-of-freedom robotic arm. The results highlight the importance of incorporating directional constraints in pHRI for hierarchical tasks. Compared to existing methods, our approach generates smoother robotic trajectories during interaction while avoiding interaction delays at the constraint boundaries.

Component Selection for Craft Assembly Tasks

Inspired by traditional handmade crafts, where a person improvises assemblies based on the available objects, we formally introduce the Craft Assembly Task. It is a robotic assembly task that involves building an accurate representation of a given target object using the available objects, which do not directly correspond to its parts. In this work, we focus on selecting the subset of available objects for the final craft, when the given input is an RGB image of the target in the wild. We use a mask segmentation neural network to identify visible parts, followed by retrieving labelled template meshes. These meshes undergo pose optimization to determine the most suitable template. Then, we propose to simplify the parts of the transformed template mesh to primitive shapes like cuboids or cylinders. Finally, we design a search algorithm to find correspondences in the scene based on local and global proportions. We develop baselines for comparison that consider all possible combinations, and choose the highest scoring combination for common metrics used in foreground maps and mask accuracy. Our approach achieves comparable results to the baselines for two different scenes, and we show qualitative results for an implementation in a real-world scenario.

Functional Eigen-Grasping Using Approach Heatmaps

This work presents a framework for a robot with a multi-fingered hand to freely utilize daily tools, including functional parts like buttons and triggers. An approach heatmap is generated by selecting a functional finger, indicating optimal palm positions on the object's surface that enable the functional finger to contact the tool's functional part. Once the palm position is identified through the heatmap, achieving the functional grasp becomes a straightforward process where the fingers stably grasp the object with low-dimensional inputs using the eigengrasp. As our approach does not need human demonstrations, it can easily adapt to various sizes and designs, extending its applicability to different objects. In our approach, we use directional manipulability to obtain the approach heatmap. In addition, we add two kinds of energy functions, i.e., palm energy and functional energy functions, to realize the eigengrasp. Using this method, each robotic gripper can autonomously identify its optimal workspace for functional grasping, extending its applicability to non-anthropomorphic robotic hands. We show that several daily tools like spray, drill, and remotes can be efficiently used by not only an anthropomorphic Shadow hand but also a non-anthropomorphic Barrett hand.

Robotic Test Tube Rearrangement Using Combined Reinforcement Learning and Motion Planning

A combined task-level reinforcement learning and motion planning framework is proposed in this paper to address a multi-class in-rack test tube rearrangement problem. At the task level, the framework uses reinforcement learning to infer a sequence of swap actions while ignoring robotic motion details. At the motion level, the framework accepts the swapping action sequences inferred by task-level agents and plans the detailed robotic pick-and-place motion. The task and motion-level planning form a closed loop with the help of a condition set maintained for each rack slot, which allows the framework to perform replanning and effectively find solutions in the presence of low-level failures. Particularly for reinforcement learning, the framework leverages a distributed deep Q-learning structure with the Dueling Double Deep Q Network (D3QN) to acquire near-optimal policies and uses an A${}^\star$-based post-processing technique to amplify the collected training data. The D3QN and distributed learning help increase training efficiency. The post-processing helps complete unfinished action sequences and remove redundancy, thus making the training data more effective. We carry out both simulations and real-world studies to understand the performance of the proposed framework. The results verify the performance of the RL and post-processing and show that the closed-loop combination improves robustness. The framework is ready to incorporate various sensory feedback. The real-world studies also demonstrated the incorporation.

Many-Objective-Optimized Semi-Automated Robotic Disassembly Sequences

This study tasckles the problem of many-objective sequence optimization for semi-automated robotic disassembly operations. To this end, we employ a many-objective genetic algorithm (MaOGA) algorithm inspired by the Non-dominated Sorting Genetic Algorithm (NSGA)-III, along with robotic-disassembly-oriented constraints and objective functions derived from geometrical and robot simulations using 3-dimensional (3D) geometrical information stored in a 3D Computer-Aided Design (CAD) model of the target product. The MaOGA begins by generating a set of initial chromosomes based on a contact and connection graph (CCG), rather than random chromosomes, to avoid falling into a local minimum and yield repeatable convergence. The optimization imposes constraints on feasibility and stability as well as objective functions regarding difficulty, efficiency, prioritization, and allocability to generate a sequence that satisfies many preferred conditions under mandatory requirements for semi-automated robotic disassembly. The NSGA-III-inspired MaOGA also utilizes non-dominated sorting and niching with reference lines to further encourage steady and stable exploration and uniformly lower the overall evaluation values. Our sequence generation experiments for a complex product (36 parts) demonstrated that the proposed method can consistently produce feasible and stable sequences with a 100% success rate, bringing the multiple preferred conditions closer to the optimal solution required for semi-automated robotic disassembly operations.