An important field in robotics is the optimization of controllers. Currently, robots are often treated as a black box in this optimization process, which is the reason why derivative-free optimization methods such as evolutionary algorithms or reinforcement learning are omnipresent. When gradient-based methods are used, models are kept small or rely on finite difference approximations for the Jacobian. This method quickly grows expensive with increasing numbers of parameters, such as found in deep learning. We propose the implementation of a modern physics engine, which can differentiate control parameters. This engine is implemented for both CPU and GPU. Firstly, this paper shows how such an engine speeds up the optimization process, even for small problems. Furthermore, it explains why this is an alternative approach to deep Q-learning, for using deep learning in robotics. Finally, we argue that this is a big step for deep learning in robotics, as it opens up new possibilities to optimize robots, both in hardware and software.

The abstract can be found on the IEEE Xplore web site: http://dx.doi.org/10.1109/TNNLS.2012.2208655 c 2012 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS

Abstract-Reservoir computing (RC) is a technique in machine learning inspired by neural systems. RC has been used successfully to solve complex problems such as signal classification and signal generation. These systems are mainly implemented in software, and thereby they are limited in speed and power efficiency. Several optical and optoelectronic implementations have been demonstrated, in which the system has signals with an amplitude and phase. It is proven that these enrich the dynamics of the system, which is beneficial for the performance. In this paper, we introduce a novel optical architecture based on nanophotonic crystal cavities. This allows us to integrate many neurons on one chip, which, compared with other photonic solutions, closest resembles a classical neural network. Furthermore, the components are passive, which simplifies the design and reduces the power consumption. To assess the performance of this network, we train a photonic network to generate periodic patterns, using an alternative online learning rule called firstorder reduced and corrected error. For this, we first train a classical hyperbolic tangent reservoir, but then we vary some of the properties to incorporate typical aspects of a photonics reservoir, such as the use of continuous-time versus discretetime signals and the use of complex-valued versus real-valued signals. Then, the nanophotonic reservoir is simulated and we explore the role of relevant parameters such as the topology, the phases between the resonators, the number of nodes that are biased and the delay between the resonators. It is important that these parameters are chosen such that no strong selfoscillations occur. Finally, our results show that for a signal generation task a complex-valued, continuous-time nanophotonic reservoir outperforms a classical (i.e., discrete-time, real-valued) leaky hyperbolic tangent reservoir (normalized root-mean-square errors = 0.030 versus NRMSE = 0.127).

Robotics research in helping children with autism has gained increased attention in recent years. Children with autism often struggle with neurodevelopmental disorders that affect their lives particularly in communication skills, social interaction and their repetitive stereotyped behavior. In this article, we highlight previous findings on human-robot interaction for children with autism. To date, it has been claimed that child-robot interaction is a beneficial approach in helping children with autism to improve their quality of life. Based on an extensive search of the literature, we identified three major research gaps: (1) diversity in research focus, (2) bias contribution in robotics research towards specific behavior impairments in autism and, (3) effectiveness of human-robot interaction after robot-based intervention program. Therefore, this review paper shall identify and thoroughly discuss published works that address the research gaps found in this areas. This article is therefore seen as a crucial step in bridging the gap between robotics research and children with autism. The results presented could be beneficial for researchers in determining future directions for robotics research in helping children with autism.

No abstract