Developing a unified multi-task foundation model has become a critical challenge in computer vision research. In the current field of 3D computer vision, most datasets only focus on single task, which complicates the concurrent training requirements of various downstream tasks. In this paper, we introduce VEnvision3D, a large 3D synthetic perception dataset for multi-task learning, including depth completion, segmentation, upsampling, place recognition, and 3D reconstruction. Since the data for each task is collected in the same environmental domain, sub-tasks are inherently aligned in terms of the utilized data. Therefore, such a unique attribute can assist in exploring the potential for the multi-task model and even the foundation model without separate training methods. Meanwhile, capitalizing on the advantage of virtual environments being freely editable, we implement some novel settings such as simulating temporal changes in the environment and sampling point clouds on model surfaces. These characteristics enable us to present several new benchmarks. We also perform extensive studies on multi-task end-to-end models, revealing new observations, challenges, and opportunities for future research. Our dataset and code will be open-sourced upon acceptance.
Computational design can excite the full potential of soft robotics that has the drawbacks of being highly nonlinear from material, structure, and contact. Up to date, enthusiastic research interests have been demonstrated for individual soft fingers, but the frame design space (how each soft finger is assembled) remains largely unexplored. Computationally design remains challenging for the finger-based soft gripper to grip across multiple geometrical-distinct object types successfully. Including the design space for the gripper frame can bring huge difficulties for conventional optimisation algorithms and fitness calculation methods due to the exponential growth of high-dimensional design space. This work proposes an automated computational design optimisation framework that generates gripper diversity to individually grasp geometrically distinct object types based on a quality-diversity approach. This work first discusses a significantly large design space (28 design parameters) for a finger-based soft gripper, including the rarely-explored design space of finger arrangement that is converted to various configurations to arrange individual soft fingers. Then, a contact-based Finite Element Modelling (FEM) is proposed in SOFA to output high-fidelity grasping data for fitness evaluation and feature measurements. Finally, diverse gripper designs are obtained from the framework while considering features such as the volume and workspace of grippers. This work bridges the gap of computationally exploring the vast design space of finger-based soft grippers while grasping large geometrically distinct object types with a simple control scheme.
Among the wide variety of evolutionary computing models, Finite State Machines (FSMs) have several attractions for fundamental research. They are easy to understand in concept and can be visualised clearly in simple cases. They have a ready fitness criterion through their relationship with Regular Languages. They have also been shown to be tractably evolvable, even up to exhibiting evidence of open-ended evolution in specific scenarios. In addition to theoretical attraction, they also have industrial applications, as a paradigm of both automated and user-initiated control. Improving the understanding of the factors affecting FSM evolution has relevance to both computer science and practical optimisation of control. We investigate an evolutionary scenario of FSMs adapting to recognise one of a family of Regular Languages by categorising positive and negative samples, while also being under a counteracting selection pressure that favours fewer states. The results appear to indicate that longer strings provided as samples reduce the speed of fitness gain, when fitness is measured against a fixed number of sample strings. We draw the inference that additional information from longer strings is not sufficient to compensate for sparser coverage of the combinatorial space of positive and negative sample strings.
Micro-expression recognition (MER) draws intensive research interest as micro-expressions (MEs) can infer genuine emotions. Prior information can guide the model to learn discriminative ME features effectively. However, most works focus on researching the general models with a stronger representation ability to adaptively aggregate ME movement information in a holistic way, which may ignore the prior information and properties of MEs. To solve this issue, driven by the prior information that the category of ME can be inferred by the relationship between the actions of facial different components, this work designs a novel model that can conform to this prior information and learn ME movement features in an interpretable way. Specifically, this paper proposes a Decomposition and Reconstruction-based Graph Representation Learning (DeRe-GRL) model to effectively learn high-level ME features. DeRe-GRL includes two modules: Action Decomposition Module (ADM) and Relation Reconstruction Module (RRM), where ADM learns action features of facial key components and RRM explores the relationship between these action features. Based on facial key components, ADM divides the geometric movement features extracted by the graph model-based backbone into several sub-features, and learns the map matrix to map these sub-features into multiple action features; then, RRM learns weights to weight all action features to build the relationship between action features. The experimental results demonstrate the effectiveness of the proposed modules, and the proposed method achieves competitive performance.
How someone allocates their time is important to their health and well-being. In this paper, we show how evolutionary algorithms can be used to promote health and well-being by optimizing time usage. Based on data from a large population-based child cohort, we design fitness functions to explain health outcomes and introduce constraints for viable time plans. We then investigate the performance of evolutionary algorithms to optimize time use for four individual health outcomes with hypothetical children with different day structures. As the four health outcomes are competing for time allocations, we study how to optimize multiple health outcomes simultaneously in the form of a multi-objective optimization problem. We optimize one-week time-use plans using evolutionary multi-objective algorithms and point out the trade-offs achievable with respect to different health outcomes.
Evolutionary algorithms have been widely used for a range of stochastic optimization problems in order to address complex real-world optimization problems. We consider the knapsack problem where the profits involve uncertainties. Such a stochastic setting reflects important real-world scenarios where the profit that can be realized is uncertain. We introduce different ways of dealing with stochastic profits based on tail inequalities such as Chebyshev's inequality and Hoeffding bounds that allow to limit the impact of uncertainties. We examine simple evolutionary algorithms and the use of heavy tail mutation and a problem-specific crossover operator for optimizing uncertain profits. Our experimental investigations on different benchmarks instances show the results of different approaches based on tail inequalities as well as improvements achievable through heavy tail mutation and the problem specific crossover operator.
The Stockpile blending problem is an important component of mine production scheduling, where stockpiles are used to store and blend raw material. The goal of blending material from stockpiles is to create parcels of concentrate which contain optimal metal grades based on the material available. The volume of material that each stockpile provides to a given parcel is dependent on a set of mine schedule conditions and customer demands. Therefore, the problem can be formulated as a continuous optimization problem. In the real-world application, there are several constraints required to guarantee parcels that meet the demand of downstream customers. It is a challenge in solving the stockpile blending problems since its scale can be very large. We introduce two repaired operators for the problems to convert the infeasible solutions into the solutions without violating the two tight constraints. Besides, we introduce a multi-component fitness function for solving the large-scale stockpile blending problem which can maximize the volume of metal over the plan and maintain the balance between stockpiles according to the usage of metal. Furthermore, we investigate the well-known approach in this paper, which is used to solve optimization problems over continuous space, namely the differential evolution (DE) algorithm. The experimental results show that the DE algorithm combined with two proposed duration repair methods is significantly better in terms of the values of results than the results on real-world instances for both one-month problems and large-scale problems.
Addressing a complex real-world optimization problem is a challenging task. The chance-constrained knapsack problem with correlated uniform weights plays an important role in the case where dependent stochastic components are considered. We perform runtime analysis of a randomized search algorithm (RSA) and a basic evolutionary algorithm (EA) for the chance-constrained knapsack problem with correlated uniform weights. We prove bounds for both algorithms for producing a feasible solution. Furthermore, we investigate the behavior of the algorithms and carry out analyses on two settings: uniform profit value and the setting in which every group shares an arbitrary profit profile. We provide insight into the structure of these problems and show how the weight correlations and the different types of profit profiles influence the runtime behavior of both algorithms in the chance-constrained setting.
Heuristic algorithms have shown a good ability to solve a variety of optimization problems. Stockpile blending problem as an important component of the mine scheduling problem is an optimization problem with continuous search space containing uncertainty in the geologic input data. The objective of the optimization process is to maximize the total volume of materials of the operation and subject to resource capacities, chemical processes, and customer requirements. In this paper, we consider the uncertainty in material grades and introduce chance constraints that are used to ensure the constraints with high confidence. To address the stockpile blending problem with chance constraints, we propose a differential evolution algorithm combining two repair operators that are used to tackle the two complex constraints. In the experiment section, we compare the performance of the approach with the deterministic model and stochastic models by considering different chance constraints and evaluate the effectiveness of different chance constraints.
The chance-constrained knapsack problem is a variant of the classical knapsack problem where each item has a weight distribution instead of a deterministic weight. The objective is to maximize the total profit of the selected items under the condition that the weight of the selected items only exceeds the given weight bound with a small probability of $\alpha$. In this paper, consider problem-specific single-objective and multi-objective approaches for the problem. We examine the use of heavy-tail mutations and introduce a problem-specific crossover operator to deal with the chance-constrained knapsack problem. Empirical results for single-objective evolutionary algorithms show the effectiveness of our operators compared to the use of classical operators. Moreover, we introduce a new effective multi-objective model for the chance-constrained knapsack problem. We use this model in combination with the problem-specific crossover operator in multi-objective evolutionary algorithms to solve the problem. Our experimental results show that this leads to significant performance improvements when using the approach in evolutionary multi-objective algorithms such as GSEMO and NSGA-II.