This research will present a hybrid approach to accelerate convergence in a second order optimization. An online finite difference approximation of the diagonal Hessian matrix will be introduced, along with fuzzy inferencing of several hyperparameters. Competitive results have been achieved

Urban Air Mobility (UAM) expands vehicles from the ground to the near-ground space, envisioned as a revolution for transportation systems. Comprehensive scene perception is the foundation for autonomous aerial driving. However, UAM encounters the intelligent perception challenge: high perception learning requirements conflict with the limited sensors and computing chips of flying cars. To overcome the challenge, federated learning (FL) and other collaborative learning have been proposed to enable resource-limited devices to conduct onboard deep learning (DL) collaboratively. But traditional collaborative learning like FL relies on a central integrator for DL model aggregation, which is difficult to deploy in dynamic environments. The fully decentralized learning schemes may be the intuitive solution while the convergence of distributed learning cannot be guaranteed. Accordingly, this paper explores reconfigurable intelligent surfaces (RIS) empowered distributed learning, taking account of topological attributes to facilitate the learning performance with convergence guarantee. We propose several FL topological criteria for optimizing the transmission delay and convergence rate by exploiting the Laplacian matrix eigenvalues of the communication network. Subsequently, we innovatively leverage the RIS link modification ability to remold the current network according to the proposed topological criteria. This paper rethinks the functions of RIS from the perspective of the network layer. Furthermore, a deep deterministic policy gradient-based RIS phase shift control algorithm is developed to construct or deconstruct the network links simultaneously to reshape the communication network. Simulation experiments are conducted over MobileNet-based multi-view learning to verify the efficiency of the distributed FL framework.

We introduce a new trajectory optimization method for robotic grasping based on a point-cloud representation of robots and task spaces. In our method, robots are represented by 3D points on their link surfaces. The task space of a robot is represented by a point cloud that can be obtained from depth sensors. Using the point-cloud representation, goal reaching in grasping can be formulated as point matching, while collision avoidance can be efficiently achieved by querying the signed distance values of the robot points in the signed distance field of the scene points. Consequently, a constrained non-linear optimization problem is formulated to solve the joint motion and grasp planning problem. The advantage of our method is that the point-cloud representation is general to be used with any robot in any environment. We demonstrate the effectiveness of our method by conducting experiments on a tabletop scene and a shelf scene for grasping with a Fetch mobile manipulator and a Franka Panda arm.

Split learning (SL) is a promising approach for training artificial intelligence (AI) models, in which devices collaborate with a server to train an AI model in a distributed manner, based on a same fixed split point. However, due to the device heterogeneity and variation of channel conditions, this way is not optimal in training delay and energy consumption. In this paper, we design an adaptive split learning (ASL) scheme which can dynamically select split points for devices and allocate computing resource for the server in wireless edge networks. We formulate an optimization problem to minimize the average training latency subject to long-term energy consumption constraint. The difficulties in solving this problem are the lack of future information and mixed integer programming (MIP). To solve it, we propose an online algorithm leveraging the Lyapunov theory, named OPEN, which decomposes it into a new MIP problem only with the current information. Then, a two-layer optimization method is proposed to solve the MIP problem. Extensive simulation results demonstrate that the ASL scheme can reduce the average training delay and energy consumption by 53.7% and 22.1%, respectively, as compared to the existing SL schemes.

Parallel Quantum Annealing is a technique to solve multiple optimization problems simultaneously. Parallel quantum annealing aims to optimize the utilization of available qubits on a quantum topology by addressing multiple independent problems in a single annealing cycle. This study provides insights into the potential and the limitations of this parallelization method. The experiments consisting of two different problems are integrated, and various problem dimensions are explored including normalization techniques using specific methods such as DWaveSampler with Default Embedding, DWaveSampler with Custom Embedding and LeapHybridSampler. This method minimizes idle qubits and holds promise for substantial speed-up, as indicated by the Time-to-Solution (TTS) metric, compared to traditional quantum annealing, which solves problems sequentially and may leave qubits unutilized.

In this paper, we propose an Openspace Collision-freE trAjectory plaNner (OCEAN) for autonomous parking. OCEAN is an optimization-based trajectory planner accelerated by Alternating Direction Method of Multiplier (ADMM) with enhanced computational efficiency and robustness, and is suitable for all scenes with few dynamic obstacles. Starting from a hierarchical optimization-based collision avoidance framework, the trajectory planning problem is first warm-started by a collision-free Hybrid A* trajectory, then the collision avoidance trajectory planning problem is reformulated as a smooth and convex dual form, and solved by ADMM in parallel. The optimization variables are carefully split into several groups so that ADMM sub-problems are formulated as Quadratic Programming (QP), Sequential Quadratic Programming (SQP),and Second Order Cone Programming (SOCP) problems that can be efficiently and robustly solved. We validate our method both in hundreds of simulation scenarios and hundreds of hours of public parking areas. The results show that the proposed method has better system performance compared with other benchmarks.

Entropic optimal transport (OT) and the Sinkhorn algorithm have made it practical for machine learning practitioners to perform the fundamental task of calculating transport distance between statistical distributions. In this work, we focus on a general class of OT problems under a combination of equality and inequality constraints. We derive the corresponding entropy regularization formulation and introduce a Sinkhorn-type algorithm for such constrained OT problems supported by theoretical guarantees. We first bound the approximation error when solving the problem through entropic regularization, which reduces exponentially with the increase of the regularization parameter. Furthermore, we prove a sublinear first-order convergence rate of the proposed Sinkhorn-type algorithm in the dual space by characterizing the optimization procedure with a Lyapunov function. To achieve fast and higher-order convergence under weak entropy regularization, we augment the Sinkhorn-type algorithm with dynamic regularization scheduling and second-order acceleration. Overall, this work systematically combines recent theoretical and numerical advances in entropic optimal transport with the constrained case, allowing practitioners to derive approximate transport plans in complex scenarios.

Cooperative co-evolution (CC) algorithms, based on the divide-and-conquer strategy, have emerged as the predominant approach to solving large-scale global optimization (LSGO) problems. The efficiency and accuracy of the grouping stage significantly impact the performance of the optimization process. While the general separability grouping (GSG) method has overcome the limitation of previous differential grouping (DG) methods by enabling the decomposition of non-additively separable functions, it suffers from high computational complexity. To address this challenge, this article proposes a composite separability grouping (CSG) method, seamlessly integrating DG and GSG into a problem decomposition framework to utilize the strengths of both approaches. CSG introduces a step-by-step decomposition framework that accurately decomposes various problem types using fewer computational resources. By sequentially identifying additively, multiplicatively and generally separable variables, CSG progressively groups non-separable variables by recursively considering the interactions between each non-separable variable and the formed non-separable groups. Furthermore, to enhance the efficiency and accuracy of CSG, we introduce two innovative methods: a multiplicatively separable variable detection method and a non-separable variable grouping method. These two methods are designed to effectively detect multiplicatively separable variables and efficiently group non-separable variables, respectively. Extensive experimental results demonstrate that CSG achieves more accurate variable grouping with lower computational complexity compared to GSG and state-of-the-art DG series designs.

Symmetry is a fundamental aspect of many real-world robotic tasks. However, current deep reinforcement learning (DRL) approaches can seldom harness and exploit symmetry effectively. Often, the learned behaviors fail to achieve the desired transformation invariances and suffer from motion artifacts. For instance, a quadruped may exhibit different gaits when commanded to move forward or backward, even though it is symmetrical about its torso. This issue becomes further pronounced in high-dimensional or complex environments, where DRL methods are prone to local optima and fail to explore regions of the state space equally. Past methods on encouraging symmetry for robotic tasks have studied this topic mainly in a single-task setting, where symmetry usually refers to symmetry in the motion, such as the gait patterns. In this paper, we revisit this topic for goal-conditioned tasks in robotics, where symmetry lies mainly in task execution and not necessarily in the learned motions themselves. In particular, we investigate two approaches to incorporate symmetry invariance into DRL -- data augmentation and mirror loss function. We provide a theoretical foundation for using augmented samples in an on-policy setting. Based on this, we show that the corresponding approach achieves faster convergence and improves the learned behaviors in various challenging robotic tasks, from climbing boxes with a quadruped to dexterous manipulation.

Managing complex Cyber-Physical Energy Systems (CPES) requires solving various optimization problems with multiple objectives and constraints. As distributed control architectures are becoming more popular in CPES for certain tasks due to their flexibility, robustness, and privacy protection, multi-objective optimization must also be distributed. For this purpose, we present MO-COHDA, a fully distributed, agent-based algorithm, for solving multi-objective optimization problems of CPES. MO-COHDA allows an easy and flexible adaptation to different use cases and integration of custom functionality. To evaluate the effectiveness of MO-COHDA, we compare it to a central NSGA-2 algorithm using multi-objective benchmark functions from the ZDT problem suite. The results show that MO-COHDA can approximate the reference front of the benchmark problems well and is suitable for solving multi-objective optimization problems. In addition, an example use case of scheduling a group of generation units while optimizing three different objectives was evaluated to show how MO-COHDA can be easily applied to real-world optimization problems in CPES.