The increasing trend of studying the innate softness of robotic structures and amalgamating it with the benefits of the extensive developments in the field of embodied intelligence has led to sprouting of a relatively new yet extremely rewarding sphere of technology. The fusion of current deep reinforcement algorithms with physical advantages of a soft bio-inspired structure certainly directs us to a fruitful prospect of designing completely self-sufficient agents that are capable of learning from observations collected from their environment to achieve a task they have been assigned. For soft robotics structure possessing countless degrees of freedom, it is often not easy (something not even possible) to formulate mathematical constraints necessary for training a deep reinforcement learning (DRL) agent for the task in hand, hence, we resolve to imitation learning techniques due to ease of manually performing such tasks like manipulation that could be comfortably mimicked by our agent. Deploying current imitation learning algorithms on soft robotic systems have been observed to provide satisfactory results but there are still challenges in doing so. This review article thus posits an overview of various such algorithms along with instances of them being applied to real world scenarios and yielding state-of-the-art results followed by brief descriptions on various pristine branches of DRL research that may be centers of future research in this field of interest.

Imitation Learning is a discipline of Machine Learning primarily concerned with replicating observed behavior of agents known to perform well on a given task, collected in demonstration data sets. In this paper, we set out to introduce a pipeline for collecting demonstrations and training models that can produce motion plans for industrial robots. Object throwing is defined as the motivating use case. Multiple input data modalities are surveyed, and motion capture is selected as the most practicable. Two model architectures operating autoregressively are examined -- feedforward and recurrent neural networks. Trained models execute throws on a real robot successfully, and a battery of quantitative evaluation metrics is proposed, including extrapolated throw accuracy estimates. Recurrent neural networks outperform feedforward ones in most respects, with the best models having an assessed mean throw error on the order of 0.1...0.2 m at distances of 1.5...2.0 m. The data collection, pre-processing, and model training aspects of our proposed approach show promise, but further work is required in developing Cartesian motion planning tools before it is suitable for application in production.

I present an experimental paradigm to explore the interpersonal dynamics generating a collective mind. I hypothesized that collective organization is based on dual interpersonal modes: (1) symmetrical and (2) anti‑symmetrical. I specified the geometric topology of these modes by detecting the spatiotemporal patterns that embed cooperative agents in a three‑dimensional matrix. I found that the symmetrical mode is executed automatically and without guidance. Conversely, the anti‑symmetrical mode required explicit direction and recruited attention for execution. I demonstrate that self‑other mirror‑symmetry stabilized group dynamics, enabled fast and efficient symmetrical imitation that optimized information transmission, whereas anti‑symmetrical imitation was comparatively slow, inefficient, and unstable. I determined that the anti‑symmetrical mode spontaneously transitioned to the symmetrical mode under perturbations. Crucially, this renormalization mechanism never transitioned from symmetrical to anti‑symmetrical. These self-organizing dynamics speak to interpersonal symmetry‑breaking. In the present work, spontaneous group choice mandated that agents synchronize cooperative cycles in symmetrical space under internal or external perturbations. I provide examples to illustrate that this self-regulating pullback attractor manifests in invertebrates and vertebrates alike. I conclude by suggesting that inter‑agent symmetry provides the social stability manifold through which attention-driven interactions enable intrapersonal and interpersonal change.

The requirements for using noncyanide imitation gold plating as decorative electroplating are increasing; thus, continuously improving the quality of the coating of the imitation gold plating and optimizing the coating process have become the current priority. In this work, hydroxyethylidene diphosphonic acid (HEDP) was used as the main complexing agent, CuSO4·5H2O, ZnSO4·7H2O and NaSnO3·3H2O were the main salts, and NaOH and anhydrous sodium carbonate were used as the buffers to prepare the electroplating solution. Using sodium citrate (SC), sodium potassium tartrate (SS), sodium gluconate (SG), and glycerol (Gl) as four additives, the effects of the number of carboxyl groups on the properties of a Cu-Zn-Sn alloy coating were compared. The electrochemical analysis showed that Cu-Zn-Sn alloy codeposition occurred at -0.50 V vs. Hg|HgO. The scanning electron microscopy (SEM) results showed that the particle size of the coatings obtained with carboxyl-containing additives was more uniform than that obtained with the electroplating solution without additives. The X-ray fluorescence spectrometry (XRF) analysis revealed that the composition of the Cu-Zn-Sn alloy coating obtained by using SC as an additive in the electroplating solution was 89.75 wt% Cu, 9.61 wt% Zn, and 0.64 wt% Sn, and the color of the coating was golden yellow. The X-ray diffraction (XRD) pattern showed that the coating was a mixture of Cu, Cu5Zn8, CuSn, Cu6Sn5, and CuZn phases. The analysis of the electroplating solution by UV, IR and NMR spectroscopy methods indicates that the additives improve the coating by affecting the complexation reaction of metal ions. These results can provide technical and theoretical guidance for developing Cu-Zn-Sn ternary alloy electrodeposition technology with the new cyanide-free HEDP alkaline electroplating system.

Equipping autonomous agents for dynamic interaction and navigation is a significant challenge in intelligent transportation systems. This study aims to address this by implementing a brain-inspired model for decision-making in autonomous vehicles. We employ active inference, a Bayesian approach that models decision-making processes similar to the human brain, focusing on the agent's preferences and the principle of free energy. This approach is combined with imitation learning to enhance the vehicle's ability to adapt to new observations and make human-like decisions. The research involved developing a multi-modal self-awareness architecture for autonomous driving systems and testing this model in driving scenarios, including abnormal observations. The results demonstrated the model's effectiveness in enabling the vehicle to make safe decisions, particularly in unobserved or dynamic environments. The study concludes that the integration of active inference with imitation learning significantly improves the performance of autonomous vehicles, offering a promising direction for future developments in intelligent transportation systems.

Due to the limitations on the capabilities of current robots regarding task learning and performance, imitation is an efficient social learning approach that endows a robot with the ability to transmit and reproduce human postures, actions, behaviors, etc., as a human does. Stable whole-body imitation and task-oriented teleoperation via imitation are challenging issues. In this paper, a novel comprehensive and unrestricted real-time whole-body imitation system for humanoid robots is designed and developed. To map human motions to a robot, an analytical method called geometrical analysis based on link vectors and virtual joints (GA-LVVJ) is proposed. In addition, a real-time locomotion method is employed to realize a natural mode of operation. To achieve safe mode switching, a filter strategy is proposed. Then, two quantitative vector-set-based methods of similarity evaluation focusing on the whole body and local links, called the Whole-Body-Focused (WBF) method and the Local-Link-Focused (LLF) method, respectively, are proposed and compared. Two experiments conducted to verify the effectiveness of the proposed methods and system are reported. Specifically, the first experiment validates the good stability and similarity features of our system, and the second experiment verifies the effectiveness with which complicated tasks can be executed. At last, an imitation learning mechanism in which the joint angles of demonstrators are mapped by GA-LVVJ is presented and developed to extend the proposed system.

Manipulating cloth-like deformable objects (CDOs) is a long-standing problem in the robotics community. CDOs are flexible (non-rigid) objects that do not show a detectable level of com- pression strength while two points on the article are pushed towards each otherand include objects such as ropes (1D), fabrics (2D) and bags (3D). In general, CDOs’ many degrees of freedom (DoF) introduce severe self-occlusion and complex state-action dynamics as significant obstacles for perception and manipulation systems. These challenges exacerbate existing issues of modern robotic control methods such as imitation learning (IL) and reinforcement learning (RL). This review focuses on the application details of data-driven control methods on four major task families in this domain: cloth-shaping, rope manipulation, dressing and bag manip- ulation. Furthermore, we identify specific inductive biases in these four domains that present challenges for more general IL and RL algorithms, and summarise the future direction for the development of the field.