Retraction: Co3 O4 Polyhedron@MnO2 Nanotube Composite as Anode for High-Performance Lithium-Ion Batteries.

Small 2021, 17, 2008165 DOI: 10.1002/smll.202008165 The above article in Small, published online on 26 March 2021 in Wiley Online Library (https://onlinelibrary.wiley.com/doi/abs/10.1002/smll.202008165),[1] has been retracted by agreement between the authors, the Editor-in-Chief, José Oliveira, and Wiley-VCH GmbH. The retraction has been agreed following an investigation by the corresponding author. The electrochemical measurements on the anode were performed in a wrong manner and cannot reliably be reproduced. The conclusions of this article are considered to be invalid. The authors agree with the retraction but were not available to confirm the final wording of the retraction. [1] Z. Cao, Y. Yang, J. Qin, J. He, Z. Su, Small 2021, 17, 2008165.

Co3 O4 Polyhedron@MnO2 Nanotube Composite as Anode for High-Performance Lithium-Ion Batteries.

In this work, a novel lollipop nanostructure of Co3 O4 @MnO2 composite is prepared as anode material in lithium-ion batteries (LIBs). Cobalt metal-organic framework (ZIF-67) is grown on the open end of MnO2 nanotubes via a self-assembly process. The obtained ZIF-67@MnO2 is then converted to Co3 O4 @MnO2 by a simple annealing treatment in air. Scanning electron microscopy, transmission electron microscopy, and X-ray diffraction characterizations indicate that the prepared Co3 O4 @MnO2 takes a lollipop nanostructure with a stick of ≈100 nm in diameter, consisting of MnO2 nanotube, and a head part of ≈1 µm, consisting of Co3 O4 nanoparticles. The charge-discharge tests illustrate that this unique novel configuration endows the resulting Co3 O4 @MnO2 with excellent electrochemical performances, delivering a capacity of 1080 mAh g-1 at 300 mA g-1 after 160 cycles, and 696 mAh g-1 at 1 A g-1 after 210 cycles, compared with 404 mAh g-1 and 590 for pure Co3 O4 polyhedrons and pure MnO2 nanotubes at 300 mA g-1 after 160 cycles, respectively. The lollipop configuration consisting of porous Co3 O4 polyhedron and MnO2 nanotube shows excellent structural stability and facilitates lithium insertion/extraction, leading to excellent cyclic stability and rate capacity of Co3 O4 @MnO2 -based LIBs.

DRL-Searcher: A Unified Approach to Multirobot Efficient Search for a Moving Target.

This article studies the multirobot efficient search (MuRES) for a nonadversarial moving target problem, whose objective is usually defined as either minimizing the target's expected capture time or maximizing the target's capture probability within a given time budget. Different from canonical MuRES algorithms, which target only one specific objective, our proposed algorithm, named distributional reinforcement learning-based searcher (DRL-Searcher), serves as a unified solution to both MuRES objectives. DRL-Searcher employs distributional reinforcement learning (DRL) to evaluate the full distribution of a given search policy's return, that is, the target's capture time, and thereafter makes improvements with respect to the particularly specified objective. We further adapt DRL-Searcher to the use case without the target's real-time location information, where only the probabilistic target belief (PTB) information is provided. Lastly, the recency reward is designed for implicit coordination among multiple robots. Comparative simulation results in a range of MuRES test environments show the superior performance of DRL-Searcher to state of the arts. Additionally, we deploy DRL-Searcher to a real multirobot system for moving target search in a self-constructed indoor environment with satisfying results.

Deep Reinforcement Learning for Solving Vehicle Routing Problems With Backhauls.

The vehicle routing problem with backhauls (VRPBs) is a challenging problem commonly studied in computer science and operations research. Featured by linehaul (or delivery) and backhaul (or pickup) customers, the VRPB has broad applications in real-world logistics. In this article, we propose a neural heuristic based on deep reinforcement learning (DRL) to solve the traditional and improved VRPB variants, with an encoder-decoder structured policy network trained to sequentially construct the routes for vehicles. Specifically, we first describe the VRPB based on a graph and cast the solution construction as a Markov decision process (MDP). Then, to identify the relationship among the nodes (i.e., linehaul and backhaul customers, and the depot), we design a two-stage attention-based encoder, including a self-attention and a heterogeneous attention for each stage, which could yield more informative representations of the nodes so as to deliver high-quality solutions. The evaluation on the two VRPB variants reveals that, our neural heuristic performs favorably against both the conventional and neural heuristic baselines on randomly generated instances and benchmark instances. Moreover, the trained policy network exhibits a desirable capability of generalization to various problem sizes and distributions.

Conditional Neural Heuristic for Multiobjective Vehicle Routing Problems.

Existing neural heuristics for multiobjective vehicle routing problems (MOVRPs) are primarily conditioned on instance context, which failed to appropriately exploit preference and problem size, thus holding back the performance. To thoroughly unleash the potential, we propose a novel conditional neural heuristic (CNH) that fully leverages the instance context, preference, and size with an encoder-decoder structured policy network. Particularly, in our CNH, we design a dual-attention-based encoder to relate preferences and instance contexts, so as to better capture their joint effect on approximating the exact Pareto front (PF). We also design a size-aware decoder based on the sinusoidal encoding to explicitly incorporate the problem size into the embedding, so that a single trained model could better solve instances of various scales. Besides, we customize the REINFORCE algorithm to train the neural heuristic by leveraging stochastic preferences (SPs), which further enhances the training performance. Extensive experimental results on random and benchmark instances reveal that our CNH could achieve favorable approximation to the whole PF with higher hypervolume (HV) and lower optimality gap (Gap) than those of the existing neural and conventional heuristics. More importantly, a single trained model of our CNH can outperform other neural heuristics that are exclusively trained on each size. In addition, the effectiveness of the key designs is also verified through ablation studies.

Learning to Solve 3-D Bin Packing Problem via Deep Reinforcement Learning and Constraint Programming.

Recently, there is a growing attention on applying deep reinforcement learning (DRL) to solve the 3-D bin packing problem (3-D BPP). However, due to the relatively less informative yet computationally heavy encoder, and considerably large action space inherent to the 3-D BPP, existing DRL methods are only able to handle up to 50 boxes. In this article, we propose to alleviate this issue via a DRL agent, which sequentially addresses three subtasks of sequence, orientation, and position, respectively. Specifically, we exploit a multimodal encoder, where a sparse attention subencoder embeds the box state to mitigate the computation while learning the packing policy, and a convolutional neural network subencoder embeds the view state to produce auxiliary spatial representation. We also leverage an action representation learning in the decoder to cope with the large action space of the position subtask. Besides, we integrate the proposed DRL agent into constraint programming (CP) to further improve the solution quality iteratively by exploiting the powerful search framework in CP. The experiments show that both the sole DRL and hybrid methods enable the agent to solve large-scale instances of 120 boxes or more. Moreover, they both could deliver superior performance against the baselines on instances of various scales.

Learning Feature Embedding Refiner for Solving Vehicle Routing Problems.

While the encoder-decoder structure is widely used in the recent neural construction methods for learning to solve vehicle routing problems (VRPs), they are less effective in searching solutions due to deterministic feature embeddings and deterministic probability distributions. In this article, we propose the feature embedding refiner (FER) with a novel and generic encoder-refiner-decoder structure to boost the existing encoder-decoder structured deep models. It is model-agnostic that the encoder and the decoder can be from any pretrained neural construction method. Regarding the introduced refiner network, we design its architecture by combining the standard gated recurrent units (GRU) cell with two new layers, i.e., an accumulated graph attention (AGA) layer and a gated nonlinear (GNL) layer. The former extracts dynamic graph topological information of historical solutions stored in a diversified solution pool to generate aggregated pool embeddings that are further improved by the GRU, and the latter adaptively refines the feature embeddings from the encoder with the guidance of the improved pool embeddings. To this end, our FER allows current neural construction methods to not only iteratively refine the feature embeddings for boarder search range but also dynamically update the probability distributions for more diverse search. We apply FER to two prevailing neural construction methods including attention model (AM) and policy optimization with multiple optima (POMO) to solve the traveling salesman problem (TSP) and the capacitated VRP (CVRP). Experimental results show that our method achieves lower gaps and better generalization than the original ones and also exhibits competitive performance to the state-of-the-art neural improvement methods.

Learning Improvement Heuristics for Solving Routing Problems.

Recent studies in using deep learning (DL) to solve routing problems focus on construction heuristics, whose solutions are still far from optimality. Improvement heuristics have great potential to narrow this gap by iteratively refining a solution. However, classic improvement heuristics are all guided by handcrafted rules that may limit their performance. In this article, we propose a deep reinforcement learning framework to learn the improvement heuristics for routing problems. We design a self-attention-based deep architecture as the policy network to guide the selection of the next solution. We apply our method to two important routing problems, i.e., the traveling salesman problem (TSP) and the capacitated vehicle routing problem (CVRP). Experiments show that our method outperforms state-of-the-art DL-based approaches. The learned policies are more effective than the traditional handcrafted ones and can be further enhanced by simple diversifying strategies. Moreover, the policies generalize well to different problem sizes, initial solutions, and even real-world data set.

Deep Reinforcement Learning for Solving the Heterogeneous Capacitated Vehicle Routing Problem.

Existing deep reinforcement learning (DRL)-based methods for solving the capacitated vehicle routing problem (CVRP) intrinsically cope with a homogeneous vehicle fleet, in which the fleet is assumed as repetitions of a single vehicle. Hence, their key to construct a solution solely lies in the selection of the next node (customer) to visit excluding the selection of vehicle. However, vehicles in real-world scenarios are likely to be heterogeneous with different characteristics that affect their capacity (or travel speed), rendering existing DRL methods less effective. In this article, we tackle heterogeneous CVRP (HCVRP), where vehicles are mainly characterized by different capacities. We consider both min-max and min-sum objectives for HCVRP, which aim to minimize the longest or total travel time of the vehicle(s) in the fleet. To solve those problems, we propose a DRL method based on the attention mechanism with a vehicle selection decoder accounting for the heterogeneous fleet constraint and a node selection decoder accounting for the route construction, which learns to construct a solution by automatically selecting both a vehicle and a node for this vehicle at each step. Experimental results based on randomly generated instances show that, with desirable generalization to various problem sizes, our method outperforms the state-of-the-art DRL method and most of the conventional heuristics, and also delivers competitive performance against the state-of-the-art heuristic method, that is, slack induction by string removal. In addition, the results of extended experiments demonstrate that our method is also able to solve CVRPLib instances with satisfactory performance.

Highly Selective Biomimetic Flexible Tactile Sensor for Neuroprosthetics.

Biomimetic flexible tactile sensors endow prosthetics with the ability to manipulate objects, similar to human hands. However, it is still a great challenge to selectively respond to static and sliding friction forces, which is crucial tactile information relevant to the perception of weight and slippage during grasps. Here, inspired by the structure of fingerprints and the selective response of Ruffini endings to friction forces, we developed a biomimetic flexible capacitive sensor to selectively detect static and sliding friction forces. The sensor is designed as a novel plane-parallel capacitor, in which silver nanowire-3D polydimethylsiloxane (PDMS) electrodes are placed in a spiral configuration and set perpendicular to the substrate. Silver nanowires are uniformly distributed on the surfaces of 3D polydimethylsiloxane microcolumns, and silicon rubber (Ecoflex®) acts as the dielectric material. The capacitance of the sensor remains nearly constant under different applied normal forces but increases with the static friction force and decreases when sliding occurs. Furthermore, aiming at the slippage perception of neuroprosthetics, a custom-designed signal encoding circuit was designed to transform the capacitance signal into a bionic pulsed signal modulated by the applied sliding friction force. Test results demonstrate the great potential of the novel biomimetic flexible sensors with directional and dynamic sensitivity of haptic force for smart neuroprosthetics.

Stretchable, self-healing, transient macromolecular elastomeric gel for wearable electronics.

Flexible and stretchable electronics are emerging in mainstream technologies and represent promising directions for future lifestyles. Multifunctional stretchable materials with a self-healing ability to resist mechanical damage are highly desirable but remain challenging to create. Here, we report a stretchable macromolecular elastomeric gel with the unique abilities of not only self-healing but also transient properties at room temperature. By inserting small molecule glycerol into hydroxyethylcellulose (HEC), forming a glycerol/hydroxyethylcellulose (GHEC) macromolecular elastomeric gel, dynamic hydrogen bonds occur between the HEC chain and the guest small glycerol molecules, which endows the GHEC with an excellent stretchability (304%) and a self-healing ability under ambient conditions. Additionally, the GHEC elastomeric gel is completely water-soluble, and its degradation rate can be tuned by adjusting the HEC molecular weight and the ratio of the HEC to glycerol. We demonstrate several flexible and stretchable electronics devices, such as self-healing conductors, transient transistors, and electronic skins for robots based on the GHEC elastomeric gel to illustrate its multiple functions.

Insight into the Mechanism of Improved Interfacial Properties between Electrodes and Electrolyte in the Graphite/LiNi0.6Mn0.2Co0.2O2 Cell via Incorporation of 4-Propyl-[1,3,2]dioxathiolane-2,2-dioxide (PDTD).

4-Propyl-[1,3,2]dioxathiolane-2,2-dioxide (PDTD) has been investigated as an electrolyte additive for the graphite/LiNi0.6Mn0.2Co0.2O2 pouch cell. A significant improvement on the initial Coulombic efficiency and cycling stability has been achieved by incorporating 1.0 wt % PDTD additive. Specifically, initial Coulombic efficiency increased from 83.7% (baseline) to 87.8% (w/w, 1.0 wt % PDTD), and from 75.7% to 83.7% for capacity retention after 500 cycles upon cycling at room temperature. Improvements in the interfacial properties between cathode and electrolyte as well as between anode and electrolyte through incorporation of 1.0 wt % PDTD are believed to account for the observed enhanced cell performance. Insight into the mechanism of improved interfacial properties between electrodes and electrolyte in the graphite/LiNi0.6Mn0.2Co0.2O2 system has been addressed with a combination of theoretical computation and experimental techniques, including electrochemical methods and spectroscopic characterization.

Improved Li-storage performance with PEDOT-decorated MnO2 nanoboxes.

In this paper, MnO2 nanoboxes coated with poly(3,4-ethylenedioxythiophene) film (denoted as MnO2@PEDOT) are investigated as an anode material in lithium-ion batteries. The MnO2 nanoboxes are developed through the surface chemical oxidation decomposition of MnCO3 cubes and the subsequent removal of their remaining cores. PEDOT is coated on the surface of MnO2 nanoboxes via in situ polymerization of 3,4-ethylenedioxythiophene. The charge-discharge tests demonstrate that this special configuration endows the resulting MnO2@PEDOT with remarkable electrochemical performances, that is a reversible capacity of 628 mA h g-1 after 850 cycles at a current density of 1000 mA g-1 and a rate capacity of 367 mA h g-1 at 3000 mA g-1. The results indicate that the nanoboxes provide the paths for Li-ion diffusion, the reaction sites for Li-ion intercalation/deintercalation and the space to buffer the volume change during the charge-discharge process, while the conductive polymer ensures the structural stability and improves the electronic conductive property of MnO2.