Deep reinforcement learning (DRL) has made sig-nificant achievements in many real-world applications. But these real-world applications typically can only provide partial ob-servations for making decisions due to occlusions and noisy sensors. However, partial state observability can be used to hide malicious behaviors for backdoors. In this paper, we explore the sequential nature of DRL and propose a novel temporal-pattern backdoor attack to DRL, whose trigger is a set of temporal constraints on a sequence of observations rather than a single observation, and effect can be kept in a controllable duration rather than in the instant. We validate our proposed backdoor attack to a typical job scheduling task in cloud computing. Numerous experimental results show that our backdoor can achieve excellent effectiveness, stealthiness, and sustainability. Our backdoor's average clean data accuracy and attack success rate can reach 97.8% and 97.5%, respectively.

Real-world fabrics often possess complicated nonlinear, anisotropic bending stiffness properties. Measuring the physical parameters of such properties for physics-based simulation is difficult yet unnecessary, due to the persistent existence of numerical errors in simulation technology. In this work, we propose to adopt a simulation-in-the-loop strategy: instead of measuring the physical parameters, we estimate the simulation parameters to minimize the discrepancy between reality and simulation. This strategy offers good flexibility in test setups, but the associated optimization problem is computationally expensive to solve by numerical methods. Our solution is to train a regression-based neural network for inferring bending stiffness parameters, directly from drape features captured in the real world. Specifically, we choose the Cusick drape test method and treat multiple-view depth images as the feature vector. To effectively and efficiently train our network, we develop a highly expressive and physically validated bending stiffness model, and we use the traditional cantilever test to collect the parameters of this model for 618 real-world fabrics. Given the whole parameter data set, we then construct a parameter subspace, generate new samples within the sub-space, and finally simulate and augment synthetic data for training purposes. The experiment shows that our trained system can replace cantilever tests for quick, reliable and effective estimation of simulation-ready parameters. Thanks to the use of the system, our simulator can now faithfully simulate bending effects comparable to those in the real world.

In many practical applications, data enrichment can generate a large amount of accurate data to alleviate the problem of data scarcity. In order to make the fake data generated in data enrichment as close to the real data as possible, the data enriching model must be tuned to meet the loss requirements of multiple objectives in different scenarios, which makes it a multi-scenario many-objective optimization problem. However, due to the curse of the dimensionality of the scenario space and the objective space, the existing many-objective evolutionary algorithms cannot solve the problem in data enrichment well. To effectively handle this problem, we propose an adaptive formulation-based multi-objective evolutionary algorithm, where the aggregation function is used to reduce the dimension of the scenario space to one and the multiple objectives into three objectives through the adaptive formulation of the original problem. In this way, a multi-scenario many-objective problem is converted into a multi-objective problem which could be solved by existing multi-objective evolutionary algorithms. The proposed algorithm is applied to the practical data enrichment problem to solve the multi-scenario many-objective optimization problem and compared with NSGA-III. The experimental results demonstrate the remarkable superiority of the proposed algorithm over NSGA-III.

We present a computational design system that assists users to model, optimize, and fabricate quad-robots with soft skins. Our system addresses the challenging task of predicting their physical behavior by fully integrating the multibody dynamics of the mechanical skeleton and the elastic behavior of the soft skin. The developed motion control strategy uses an alternating optimization scheme to avoid expensive full space time-optimization, interleaving space-time optimization for the skeleton, and frame-by-frame optimization for the full dynamics. The output are motor torques to drive the robot to achieve a user prescribed motion trajectory. We also provide a collection of convenient engineering tools and empirical manufacturing guidance to support the fabrication of the designed quad-robot. We validate the feasibility of designs generated with our system through physics simulations and with a physically-fabricated prototype.