To date, commercial industrial robots only provide multi-robot coordination for their own fleet of robots and treat robots from other vendors as general obstacles. The ability to enable robots from different vendors to co-exist in the same space is crucial to prevent vendor lock-in. We present the first decentralized system that achieves coordination between a heterogeneous fleet of black box robots for which the internals of the navigation stack are presumed unmodifiable. Our system, which we call CODAK, achieves the coordination by relying on minimum set of interfaces that are commonly available on most industrial and service robots. For each robot, CODAK uses a trained recurrent neural network to anticipate collisions from externally observable metrics. Anticipated collisions are avoided using a simple, but yet effective, concurrency control scheme. We run a series of experiments in simulation and with real robots to demonstrate CODAK’s ability to enable safe navigation in different environments. We also experimentally compare CODAK with previously published white-box solutions to evaluate the penalty of black-box constraint.

In this paper, we present an unsupervised approach for frequency sub-band allocation in wireless networks using a graph-based learning method. We consider a scenario of dense deployment of subnetworks in the factory environment. The limited number of sub-bands must be optimally allocated to coordinate inter-subnetwork interference. Traditional iterative solutions may not scale to the large scale and density of subnetwork deployment due to their execution overhead limitations. Hence, we consider a data-driven approach based on graph neural networks. We model the subnetwork deployment as an interference graph and propose an unsupervised learning approach to optimize the sub-band allocation using graph neural networks. This approach is inspired by the graph colouring heuristic and the Potts model. The numerical evaluation shows that the proposed method achieves close performance to the centralized greedy colouring sub-band allocation heuristic with lower computational time complexity. In addition, it incurs reduced signalling overhead compared to iterative optimization heuristics that require all the mutual interfering channel information. We further demonstrate that the method is robust to different network settings.

Cell-free massive MIMO (CFmMIMO) is a promising paradigm to provide uniform coverage in future wireless networks. However, a fully connected CFmMIMO system where all the access points (APs) serve every user equipment (UE) makes it challenging to deploy and scale in real-time due to high computational complexity and increased signaling overhead. In this work, we study the problem of downlink power allocation in partially connected CFmMIMO (p-CFmMIMO) systems using maximal ratio transmission (MRT). We utilize the underlying geometry of the problem to propose a graph representation of the CFmMIMO system and develop a graph neural network (GNN) based power allocation strategy to maximize the minimum SINR in the system. We demonstrate that the proposed GNN model has excellent generalizability to deployment size, radio propagation morphologies, and per-AP serving density1. Our GNN can address the power allocation problem in the fully connected case, the partially connected case, and even the cellular case with magnitudes lower computational complexity compared to the conventional numerical solvers. Notably, we show that over a wide range of service scenarios, the model achieves a median spectral efficiency that is within 10% of the optimal second-order cone programming (SOCP) solution while requiring 100 times fewer FLOPS.

We propose a framework for maximizing the number of machine-type devices connected in the uplink of a Narrow-band Internet of Things (NB-IoT) network using non-orthogonal multiple access (NOMA). The system is based on the fast-uplink grant (FUG), where the base station (BS) schedules the access for active devices requesting connection. This problem is a mixed-integer non-convex problem and real-time solutions using general solvers are computationally prohibitive. The proposed scheduling solution comprises efficient device clustering and optimum power allocation using a bipartite graph matching approach, termed connection throughput maximizing full matching with pruning (CTMBM). Different from the other solutions of state-of-the-art, our proposed scheme considers scheduling over multiple transmission time intervals while considering the transmission deadlines and quality of service (QoS) for the devices. Additionally, we provide a method for priority scheduling of a subset of devices. We compare our solution to the state-of-the-art schemes and analyze the achieved gains through Monte-Carlo computer simulations.

Beyond 5G wireless technology Cell-Free Massive MIMO (CFmMIMO) downlink relies on carefully designed pre-coders and power control to attain uniformly high rate coverage. Many such power control problems can be calculated via second order cone programming (SOCP). In practice, several order of magnitude faster numerical procedure is required because power control has to be rapidly updated to adapt to changing channel conditions. We propose a Graph Neural Network (GNN) based solution to replace SOCP. Specifically, we develop a GNN to obtain downlink max-min power control for a CFmMIMO with maximum ratio transmission (MRT) beamforming. We construct a graph representation of the problem that properly captures the dominant dependence relationship between access points (APs) and user equipments (UEs). We exploit a symmetry property, called permutation equivariance, to attain training simplicity and efficiency. Simulation results show the superiority of our approach in terms of computational complexity, scalability and generaliz-ability for different system sizes and deployment scenarios.

We develop a framework for maximizing the number of transmitted packets for devices in a Narrowband Internet of Things (NB-IoT) network using non-orthogonal multiple access (NOMA) in the downlink. The base station (BS) chooses one of the multiple available physical resource blocks (PRBs) that are well separated in frequency for a device, giving them the advantage of exploiting frequency diversity. The scheduling strategy focuses on the two-fold problem involving efficient device clustering and optimum power allocation. This problem is a mixed-integer non-convex problem. We propose a bipartite graph matching approach, termed minimum weight full matching with pruning (MWFMP), to address the problem over multiple PRBs and solve it under the quality-of-service (QoS), allowable PRB, power budget, and interference constraints. Additionally, we provide a comparison with a greedy heuristic, the multi-PRB stratified device allocation (MPSDA), where we extend our previous work for a single PRB connectivity problem. Furthermore, we compare our algorithms to orthogonal multiple access (OMA) scheduling, which is prevalent in legacy LTE networks. We show that our algorithms steadily outperform the connectivity performance offered by OMA.

Cell-Free Massive MIMO with MRT (Maximum-Ratio Transmission) has the advantage of decentralized beam-forming with the smallest front-haul overhead. Its downlink power control plays a dual role of fair power distribution among users and interference mitigation. It is well-known that finding the optimal max-min power control relies on SOCP (Second Order Cone Programming) feasibility bisection search, whose large computational delay is not suitable for practical implementation. In this paper, we devise a deep learning approach for finding a practical near-optimal power control. Specifically, we propose a convolutional neural network that takes as input the channel matrix of large-scale fading coefficients and outputs the total transmit power of each AP (access point). Using this information, the downlink power control for each user is then computed by a low-complexity convex program. Our approach requires to generate far fewer training examples than existing schemes. The reason is that we augment the training dataset with magnitudes larger number of artificial examples by exploiting the special structure of the problem. The resulting deep learning model not only provides a near-optimal solution to the original problem, but also generalizes well for problems with different number of users and different propagation morphologies, without the need to retrain it. Numerical simulations validate the near optimality of our solution with a significant reduction in computational burden.

We envision swarms of mm-scale micro-robots to be able to carry out critical missions such as exploration and mapping for hazard detection and search and rescue. These missions share the need to reach full coverage of the explorable space and build a complete map of the environment. To minimize completion time, robots in the swarm must be able to exchange information about the environment with each other. However, communication between swarm members is often assumed to be perfect, an assumption that does not reflect real-world conditions, where impairments can affect the Packet Delivery Ratio (PDR) of the wireless links. This paper studies how communication impairments can have a drastic impact on the performance of a robotic swarm. We present Atlas 2.0, an exploration algorithm that natively takes packet loss into account. We simulate the effect of various PDRs on robotic swarm exploration and mapping in three different scenarios. Our results show that the time it takes to complete the mapping mission increases significantly as the PDR decreases: on average, halving the PDR triples the time it takes to complete mapping. We emphasise the importance of considering methods to compensate for the delay caused by lossy communication when designing and implementing algorithms for robotics swarm coordination.

We address the issue of maximizing the number of connected devices in a Narrowband Internet-of-Things (NB-IoT) network using nonorthogonal multiple access (NOMA) in the downlink. We first propose an optimal joint subcarrier and power allocation strategy assuming perfect channel state information (CSI) called stratified device allocation (SDA), which maximizes the connectivity under data rate, power, and bandwidth constraints. Then, we generalize the connectivity maximization problem to the case of partial CSI, where only the distance-dependent path-loss component of the channel gain is available at the base station (BS). We introduce a novel framework called the stochastic connectivity optimization (SCO) framework. In this framework, we propose a heuristic improvement to SDA, namely, SDA with excess power (SDA-EP) algorithm for operation under partial CSI. Furthermore, we derive a concave approximation (SCO-CA) algorithm of near-optimal performance to SCO given the same amount of CSI. Through computer simulations, we show that SDA-EP and SCO-CA outperform conventional NOMA and OMA schemes in the presence of partial CSI over a wide range of service scenarios.

Edge side caching assisted device-to-device (D2D) communication has been acknowledged as a promising technique to alleviate the heavy burden of backhaul transmission link and to reduce the network latency. However, the effectiveness of caching strategies at the network edge is highly dependent on the distribution of individual user’s content preference. To fully attain the benefits of edge caching, some proactive mechanisms shall be considered. Among which, recommendation performs noticeably well due to its capability of reshaping the content request probabilities of different users, which in turn affects the cache decision significantly. In this work, we quantitatively investigate how recommendation can be applied to enhance the caching efficiency of D2D enabled wireless content caching networks. And for that, the cache hit ratio maximization problem for a generic network model is formulated taking into account the requirements of each user’s personalized recommendation quality, recommendation quantity and cache capacity. Then, we show that the optimal recommendation and caching policies which jointly maximize the cache efficiency is NP-hard to compute. Further, a time-efficient sub-optimal algorithm is designed, which works in an iterative manner and has provable convergence guarantee as well as polynomial time complexity. Monte-Carlo simulation results demonstrate the convergence performance of our proposed joint decision algorithm and its cache efficiency improvements compared to extensive benchmarks.

Irregular Repetition Slotted Aloha (IRSA) is one candidate member of a family of random access protocols to provide solutions for massive parallel connections in the Internet of Things (IoT) networks. The key features of this protocol are repeating the transmitted packets several times and using Successive Interference Cancellation (SIC) at the decoder to resolve the collisions, which dramatically increases the performance of Slotted ALOHA. Motivated by multiple previous studies of IRSA performance in different settings, we focus on the scenario of an IoT network where the packets of different nodes are received with different powers at the base station, either per design due to different transmission power, or induced by the fact that the nodes are at different distances from the base station. In such a scenario, the capture effect emerges at the receiver, which in turn enhances the protocol performance. We analyze the protocol behavior using a new density evolution which is based on dividing nodes into classes with different powers. By computing the probability to decode a packet in the presence of the interference, we explore the achievable throughput and its associated gain and show the excellent performance of Multi-Power IRSA.

We address the issue of maximizing the number of connected devices in a Narrowband Internet of Things (NB-IoT) network using non-orthogonal multiple access (NOMA). The scheduling assignment is done on a per-transmit time interval (TTI) basis and focuses on efficient device clustering. We formulate the problem as a combinatorial optimization problem and solve it under interference, rate and sub-carrier availability constraints. We first present the bottom-up power filling algorithm (BU), which solves the problem given that each device can only be allocated contiguous sub-carriers. Then, we propose the item clustering heuristic (IC) which tackles the more general problem of non-contiguous allocation. The novelty of our optimization framework is two-fold. First, it allows any number of devices to be multiplexed per sub-carrier, which is based on the successive interference cancellation (SIC) capabilities of the network. Secondly, whereas most existing works only consider contiguous sub-carrier allocation, we also study the performance of allocating non-contiguous sub-carriers to each device. We show through extensive simulations that non-contiguous allocation through IC scheme can outperform BU and other existing contiguous allocation methods.

Future wireless communication systems have been imposed high requirement on power efficiency for operator's profitability as well as to alleviate information and communication technology (ICT) global carbon emission. To meet these challenges, the power consumption minimization problem for a generic multi-cell multiple input and single output non-orthogonal multiple access (MISO-NOMA) system is studied in this work. The associated joint user grouping, beamforming (BF) and power control problem is a mixed integer non-convex programming problem, which is tackled by an iterative distributed methodology. Towards this end, the near-optimal zero-forcing (ZF) BF is leveraged, wherein the semiorthogonal user selection (SUS) strategy is applied to select BF users. Based on these, the BF vectors and BF users are determined for each cell using only local information. Then, two distributed user grouping strategies are proposed. The first one, called channel condition based user clustering (CCUC), performs user grouping in each cell based on the channel conditions. This is conducted independently of the power control part and has low computational complexity. Another algorithm, called power consumption based user clustering (PCUC), uses both the channel conditions and inter-cell interference information to minimize each cell's power consumption. In contrary to CCUC, PCUC is optimized jointly with the power control. Finally, with the obtained user grouping and BF vectors, the resultant power allocation problem is optimally solved via an iterative algorithm, whose convergence is mathematically proven given that the problem is feasible. We perform Monte-Carlo simulation and numerical results show that the proposed resource management methods outperform various conventional MISO schemes and the non-clustered MISO-NOMA strategy in several aspects, including power consumption, outage probability, energy efficiency, and connectivity efficiency.

Non-orthogonal multiple access (NOMA) has received significant attention for future wireless networks. NOMA outperforms orthogonal schemes, such as OFDMA, in terms of spectral efficiency and massive connectivity. The joint subcarrier and power allocation problem in NOMA is NP-hard to solve in general, due to complex impacts of signal superposition on each users achievable data rates, as well as combinatorial constraints on the number of multiplexed users per sub-carrier to mitigate error propagation. In this family of problems, weighted sum-rate (WSR) is an important objective function as it can achieve different tradeoffs between sum-rate performance and user fairness. We propose a novel approach to solve the WSR maximization problem in multi-carrier NOMA with cellular power constraint. The problem is divided into two polynomial time solvable sub-problems. First, the multi-carrier power control (given a fixed subcarrier allocation) is non-convex. By taking advantage of its separability property, we design an optimal and low complexity algorithm (MCPC) based on projected gradient descent. Secondly, the single-carrier user selection is a non-convex mixed-integer problem that we solve using dynamic programming (SCUS). This work also aims to give an understanding on how each sub-problem's particular structure can facilitate the algorithm design. In that respect, the above MCPC and SCUS are basic building blocks that can be applied in a wide range of resource allocation problems. Furthermore, we propose an efficient heuristic to solve the general WSR maximization problem by combining MCPC and SCUS. Numerical results show that it achieves near-optimal sum-rate with user fairness, as well as significant performance improvement over OMA.

Non-orthogonal multiple access (NOMA) is a promising radio access technology for 5G. It allows several users to transmit on the same frequency and time resource by performing power- domain multiplexing. At the receiver side, successive interference cancellation (SIC) is applied to mitigate interference among the multiplexed signals. In this way, NOMA can outperform orthogonal multiple access schemes used in conventional cellular networks in terms of spectral efficiency and allows more simultaneous users. This paper investigates the computational complexity of joint subcarrier and power allocation problems in multi-carrier NOMA systems. We prove that these problems are strongly NP-hard for a large class of objective functions, namely the weighted generalized means of the individual data rates. This class covers the popular weighted sum-rate, proportional fairness, harmonic mean and max-min fairness utilities. Our results show that the optimal power and subcarrier allocation cannot be computed in polynomial time in the general case, unless P = NP. Nevertheless, we present some tractable special cases and we show that they can be solved efficiently.

In this paper, we investigate the distributed power allocation algorithm for the downlink of a two-cell multiple input and single output non- orthogonal multiple access (MISO-NOMA) system. The problem targets at minimizing the total power consumption of the base stations (BSs) while taking into consideration each user's data rate requirement. A distributed power control algorithm is devised. During each iteration, the BS updates the transmit power of its attached users according to the link gain vector and the inter-cell interference plus noise value at the users. For some special cases, we show that the proposed algorithm is guaranteed to converge to a unique fixed point that could be an optimal solution based on Yate's power control framework. Furthermore, some modifications are made for the iterative algorithm to enhance the convergence performance of the instances with feasible solutions. Simulation results demonstrate that the designed power allocation strategy can significantly improve system performance over conventional orthogonal multiple access (OMA) counterpart in terms of total transmit power and outage probability.

International audience