Yi Ren

Yi Chen, Lei Zhang, Tanner Merry et al.

Human-robot interactions (HRI) can be modeled as dynamic or differential games with incomplete information, where each agent holds private reward parameters. Due to the open challenge in finding perfect Bayesian equilibria of such games, existing studies often consider approximated solutions composed of parameter estimation and motion planning steps, in order to decouple the belief and physical dynamics. In parameter estimation, current approaches often assume that the reward parameters of the robot are known by the humans. We argue that by falsely conditioning on this assumption, the robot performs non-empathetic estimation of the humans' parameters, leading to undesirable values even in the simplest interactions. We test this argument by studying a two-vehicle uncontrolled intersection case with short reaction time. Results show that when both agents are unknowingly aggressive (or non-aggressive), empathy leads to more effective parameter estimation and higher reward values, suggesting that empathy is necessary when the true parameters of agents mismatch with their common belief. The proposed estimation and planning algorithms are therefore more robust than the existing approaches, by fully acknowledging the nature of information asymmetry in HRI. Lastly, we introduce value approximation techniques for real-time execution of the proposed algorithms.

Namwoo Kang, Yi Ren, Fred Feinberg et al.

Visual design is critical to product success, and the subject of intensive marketing research effort. Yet visual elements, due to their holistic and interactive nature, do not lend themselves well to optimization using extant decompositional methods for preference elicitation. Here we present a systematic methodology to incorporate interactive, 3D-rendered product configurations into a conjoint-like framework. The method relies on rapid, scalable machine learning algorithms to adaptively update product designs along with standard information-oriented product attributes. At its heart is a parametric account of a product's geometry, along with a novel, adaptive "bi-level" query task that can estimate individuals' visual design form preferences and their trade-offs against such traditional elements as price and product features. We illustrate the method's performance through extensive simulations and robustness checks, a formal proof of the bi-level query methodology's domain of superiority, and a field test for the design of a mid-priced sedan, using real-time 3D rendering for an online panel. Results indicate not only substantially enhanced predictive accuracy, but two quantities beyond the reach of standard conjoint methods: trade-offs between form and function overall, and willingness-to-pay for specific design elements. Moreover -- and most critically for applications -- the method provides "optimal" visual designs for both individuals and model-derived or analyst-supplied consumer groupings, as well as their sensitivities to form and functional elements.

Houpu Yao, Malcolm Regan, Yezhou Yang et al.

We demonstrate in this paper that a generative model can be designed to perform classification tasks under challenging settings, including adversarial attacks and input distribution shifts. Specifically, we propose a conditional variational autoencoder that learns both the decomposition of inputs and the distributions of the resulting components. During test, we jointly optimize the latent variables of the generator and the relaxed component labels to find the best match between the given input and the output of the generator. The model demonstrates promising performance at recognizing overlapping components from the multiMNIST dataset, and novel component combinations from a traffic sign dataset. Experiments also show that the proposed model achieves high robustness on MNIST and NORB datasets, in particular for high-strength gradient attacks and non-gradient attacks.

Houpu Yao, Jingjing Wen, Yi Ren et al.

Special high-end sensors with expensive hardware are usually needed to measure shock signals with high accuracy. In this paper, we show that cheap low-end sensors calibrated by deep neural networks are also capable to measure high-g shocks accurately. Firstly we perform drop shock tests to collect a dataset of shock signals measured by sensors of different fidelity. Secondly, we propose a novel network to effectively learn both the signal peak and overall shape. The results show that the proposed network is capable to map low-end shock signals to its high-end counterparts with satisfactory accuracy. To the best of our knowledge, this is the first work to apply deep learning techniques to calibrate shock sensors.

Houpu Yao, Zhe Wang, Guangyu Nie et al.

The vulnerability of neural networks under adversarial attacks has raised serious concerns and motivated extensive research. It has been shown that both neural networks and adversarial attacks against them can be sensitive to input transformations such as linear translation and rotation, and that human vision, which is robust against adversarial attacks, is invariant to natural input transformations. Based on these, this paper tests the hypothesis that model robustness can be further improved when it is adversarially trained against transformed attacks and transformation-invariant attacks. Experiments on MNIST, CIFAR-10, and restricted ImageNet show that while transformations of attacks alone do not affect robustness, transformation-invariant attacks can improve model robustness by 2.5\% on MNIST, 3.7\% on CIFAR-10, and 1.1\% on restricted ImageNet. We discuss the intuition behind this phenomenon.

Yi Ren, Steven Elliott, Yiwei Wang et al.

While intelligence of autonomous vehicles (AVs) has significantly advanced in recent years, accidents involving AVs suggest that these autonomous systems lack gracefulness in driving when interacting with human drivers. In the setting of a two-player game, we propose model predictive control based on social gracefulness, which is measured by the discrepancy between the actions taken by the AV and those that could have been taken in favor of the human driver. We define social awareness as the ability of an agent to infer such favorable actions based on knowledge about the other agent's intent, and further show that empathy, i.e., the ability to understand others' intent by simultaneously inferring others' understanding of the agent's self intent, is critical to successful intent inference. Lastly, through an intersection case, we show that the proposed gracefulness objective allows an AV to learn more sophisticated behavior, such as passive-aggressive motions that gently force the other agent to yield.

Ruijin Cang, Hope Yao, Yi Ren

We introduce a theory-driven mechanism for learning a neural network model that performs generative topology design in one shot given a problem setting, circumventing the conventional iterative process that computational design tasks usually entail. The proposed mechanism can lead to machines that quickly response to new design requirements based on its knowledge accumulated through past experiences of design generation. Achieving such a mechanism through supervised learning would require an impractically large amount of problem-solution pairs for training, due to the known limitation of deep neural networks in knowledge generalization. To this end, we introduce an interaction between a student (the neural network) and a teacher (the optimality conditions underlying topology optimization): The student learns from existing data and is tested on unseen problems. Deviation of the student's solutions from the optimality conditions is quantified, and used for choosing new data points to learn from. We call this learning mechanism "theory-driven", as it explicitly uses domain-specific theories to guide the learning, thus distinguishing itself from purely data-driven supervised learning. We show through a compliance minimization problem that the proposed learning mechanism leads to topology generation with near-optimal structural compliance, much improved from standard supervised learning under the same computational budget.