机器人相关学术速递[7.21]

访问www.arxivdaily.com获取含摘要速递，涵盖CS|物理|数学|经济|统计|金融|生物|电气领域，更有搜索、收藏、发帖等功能！点击阅读原文即可访问

cs.RO机器人相关，共计11篇

【1】 Learning to Share Autonomy Across Repeated Interaction 标题：学会在重复互动中共享自主性

作者：Ananth Jonnavittula,Dylan P. Losey 备注：8 pages, 10 figures 链接：https://arxiv.org/abs/2107.09650 摘要：安装在轮椅上的机械臂（和其他辅助机器人）应该帮助使用者完成日常任务。机器人提供这种帮助的一种方式是共享自治。在共享自治的范围内，人和机器人都保持对机器人运动的控制：当机器人对自己了解人类的需求变得自信时，它就会越来越多地介入，以实现任务的自动化。但是，机器人如何知道人类首先要执行的任务呢？今天的共享自治方法通常依赖于先验知识：例如，机器人必须事先知道一组可能的人类目标。然而，从长远来看，这种先验知识将不可避免地被打破——人类迟早会达到机器人意想不到的目标。在这篇论文中，我们提出了一个学习方法，分享自主性，利用重复互动。如果人类在每次互动中都执行完全不同的任务，那么学习帮助人类将是不可能的：但我们的见解是，身体残疾的用户每天重复重要的任务（例如，打开冰箱、煮咖啡和吃晚餐）。我们介绍了一种算法，利用这些重复的交互来识别人类的任务，复制类似的演示，并在不确定时返回控制。随着人类不断地与这个机器人合作，我们的方法不断地学习协助那些事先从未指定的任务：这些任务包括离散的目标（例如，到达一个杯子）和连续的技能（例如，打开一个抽屉）。通过仿真和现场用户研究，我们证明了机器人利用我们的方法匹配已知目标的现有共享自治方法，并在新任务上优于模仿学习基线。在此处查看视频：https://youtu.be/NazeLVbQ2og 摘要：Wheelchair-mounted robotic arms (and other assistive robots) should help their users perform everyday tasks. One way robots can provide this assistance is shared autonomy. Within shared autonomy, both the human and robot maintain control over the robot's motion: as the robot becomes confident it understands what the human wants, it increasingly intervenes to automate the task. But how does the robot know what tasks the human may want to perform in the first place? Today's shared autonomy approaches often rely on prior knowledge: for example, the robot must know the set of possible human goals a priori. In the long-term, however, this prior knowledge will inevitably break down -- sooner or later the human will reach for a goal that the robot did not expect. In this paper we propose a learning approach to shared autonomy that takes advantage of repeated interactions. Learning to assist humans would be impossible if they performed completely different tasks at every interaction: but our insight is that users living with physical disabilities repeat important tasks on a daily basis (e.g., opening the fridge, making coffee, and having dinner). We introduce an algorithm that exploits these repeated interactions to recognize the human's task, replicate similar demonstrations, and return control when unsure. As the human repeatedly works with this robot, our approach continually learns to assist tasks that were never specified beforehand: these tasks include both discrete goals (e.g., reaching a cup) and continuous skills (e.g., opening a drawer). Across simulations and an in-person user study, we demonstrate that robots leveraging our approach match existing shared autonomy methods for known goals, and outperform imitation learning baselines on new tasks. See videos here: https://youtu.be/NazeLVbQ2og

【2】 Proximal Policy Optimization for Tracking Control Exploiting Future Reference Information 标题：利用未来参考信息的跟踪控制近邻策略优化

作者：Jana Mayer,Johannes Westermann,Juan Pedro Gutiérrez H. Muriedas,Uwe Mettin,Alexander Lampe 机构：Intelligent Sensor-Actuator-Systems Laboratory (ISAS), Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology (KIT), Germany, IAV GmbH, Berlin, Germany 链接：https://arxiv.org/abs/2107.09647 摘要：近年来，强化学习在控制工程中受到越来越多的关注。尤其是政策梯度法的应用更为广泛。在这项工作中，我们通过加入未来参考值的信息来改善邻近策略优化（PPO）对任意参考信号的跟踪性能。提出了两种扩展行为人和批评家的论点，并考虑到未来的参考价值。在第一个变量中，全局未来参考值被添加到参数中。对于第二种变体，提出了一种新的具有未来参考值的剩余空间，适用于无模型强化学习。在一个简单的传动系统模型上用PI控制器对我们的方法进行了评估。我们期望我们的方法能比以前的方法更好地推广到任意引用，指出RL控制实际系统的适用性。 摘要：In recent years, reinforcement learning (RL) has gained increasing attention in control engineering. Especially, policy gradient methods are widely used. In this work, we improve the tracking performance of proximal policy optimization (PPO) for arbitrary reference signals by incorporating information about future reference values. Two variants of extending the argument of the actor and the critic taking future reference values into account are presented. In the first variant, global future reference values are added to the argument. For the second variant, a novel kind of residual space with future reference values applicable to model-free reinforcement learning is introduced. Our approach is evaluated against a PI controller on a simple drive train model. We expect our method to generalize to arbitrary references better than previous approaches, pointing towards the applicability of RL to control real systems.

【3】 Active 3D Shape Reconstruction from Vision and Touch 标题：基于视觉和触觉的主动三维形状重建

作者：Edward J. Smith,David Meger,Luis Pineda,Roberto Calandra,Jitendra Malik,Adriana Romero,Michal Drozdzal 机构： Facebook AI Research, McGill University, University of California, Berkeley 链接：https://arxiv.org/abs/2107.09584 摘要：人类通过主动探索物体，共同使用视觉和触觉，建立对世界的三维理解。然而，在三维形状重建中，最近的进展依赖于有限的感官数据（如RGB图像、深度图或触觉读数）的静态数据集，使得对形状的积极探索在很大程度上未被探索。在主动触觉三维重建中，目标是主动选择触觉读数，最大限度地提高形状重建精度。然而，基于深度学习的主动触摸模型的发展在很大程度上受到了形状探索框架的限制。本文针对这一问题，介绍了一个由以下部分组成的系统：1）基于高空间分辨率视觉的触觉传感器的触觉模拟器，用于三维物体的主动触摸；2） 基于网格的三维形状重建模型，该模型依赖于触觉或视觉信号；以及3）一组数据驱动的解决方案，具有触觉或视觉先验知识，用于指导形状探索。我们的框架支持开发第一个完全数据驱动的解决方案，以便在学习的对象理解模型之上进行主动接触。我们的实验表明，这种解决方案在三维形状理解任务中的优势，我们的模型始终优于自然基线。我们提供我们的框架作为一个工具，以促进这一方向的未来研究。 摘要：Humans build 3D understandings of the world through active object exploration, using jointly their senses of vision and touch. However, in 3D shape reconstruction, most recent progress has relied on static datasets of limited sensory data such as RGB images, depth maps or haptic readings, leaving the active exploration of the shape largely unexplored. In active touch sensing for 3D reconstruction, the goal is to actively select the tactile readings that maximize the improvement in shape reconstruction accuracy. However, the development of deep learning-based active touch models is largely limited by the lack of frameworks for shape exploration. In this paper, we focus on this problem and introduce a system composed of: 1) a haptic simulator leveraging high spatial resolution vision-based tactile sensors for active touching of 3D objects; 2) a mesh-based 3D shape reconstruction model that relies on tactile or visuotactile signals; and 3) a set of data-driven solutions with either tactile or visuotactile priors to guide the shape exploration. Our framework enables the development of the first fully data-driven solutions to active touch on top of learned models for object understanding. Our experiments show the benefits of such solutions in the task of 3D shape understanding where our models consistently outperform natural baselines. We provide our framework as a tool to foster future research in this direction.

【4】 Predicting Driver Takeover Time in Conditionally Automated Driving 标题：条件自动驾驶中驾驶员接管时间的预测

作者：Jackie Ayoub,Na Du,X. Jessie Yang,Feng Zhou 机构： Du is with the Department of Informatics and Networked Systems, School of Computing and Information, University of Pittsburgh 链接：https://arxiv.org/abs/2107.09545 摘要：在有条件的自动驾驶中，确保安全的接管过渡非常重要。量化安全接管过渡的关键因素之一是接管时间。以往的研究发现了许多因素对接管时间的影响，如接管提前期、非驱动任务、接管请求的方式和情景紧迫性。然而，目前还缺乏同时考虑这些因素来预测收购时间的研究。为此，我们使用极端梯度增强（XGBoost）来预测接管时间，使用的数据集来自荟萃分析研究[1]。此外，我们利用SHapley加性解释（SHapley Additive explaution）来分析和解释预测因子对收购时间的影响。我们确定了七个最关键的预测因子，从而产生了最好的预测性能。考察了它们对接管时间的主效应和交互效应。结果表明，该方法具有良好的性能和解释性。我们的发现对车内监控和警报系统的设计有一定的启示，以促进驾驶员和自动车辆之间的交互。 摘要：It is extremely important to ensure a safe takeover transition in conditionally automated driving. One of the critical factors that quantifies the safe takeover transition is takeover time. Previous studies identified the effects of many factors on takeover time, such as takeover lead time, non-driving tasks, modalities of the takeover requests (TORs), and scenario urgency. However, there is a lack of research to predict takeover time by considering these factors all at the same time. Toward this end, we used eXtreme Gradient Boosting (XGBoost) to predict the takeover time using a dataset from a meta-analysis study [1]. In addition, we used SHAP (SHapley Additive exPlanation) to analyze and explain the effects of the predictors on takeover time. We identified seven most critical predictors that resulted in the best prediction performance. Their main effects and interaction effects on takeover time were examined. The results showed that the proposed approach provided both good performance and explainability. Our findings have implications on the design of in-vehicle monitoring and alert systems to facilitate the interaction between the drivers and the automated vehicle.

【5】 Ontology-Assisted Generalisation of Robot Action Execution Knowledge 标题：本体辅助的机器人动作执行知识概括

作者：Alex Mitrevski,Paul G. Plöger,Gerhard Lakemeyer 机构： Pl¨oger are with the Department of ComputerScience, RWTHAachenUniversity 备注：Accepted for publication at the 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 链接：https://arxiv.org/abs/2107.09353 摘要：当一个自主机器人学习如何执行动作时，了解执行策略是否以及何时可以推广到学习场景的变化是很有意义的。这可以告知机器人需要额外学习，因为使用不完整或不合适的策略可能导致执行失败。当机器人必须在不同的环境中处理各种各样的物体时，概括就显得尤为重要。本文提出并分析了一种基于对象本体的操作行为参数化执行模型的泛化策略。特别地，机器人根据本体将已知的执行模型转移到相关类的对象，但前提是没有其他证据表明该模型可能不合适。这允许使用本体论知识作为先验信息，然后由机器人自己的经验加以提炼。我们验证了我们的算法对于抓取和收起日常物体这两个动作的有效性，从而证明了机器人可以推断出一个已有策略可以推广到其他物体的情况以及需要获取额外执行知识的情况。 摘要：When an autonomous robot learns how to execute actions, it is of interest to know if and when the execution policy can be generalised to variations of the learning scenarios. This can inform the robot about the necessity of additional learning, as using incomplete or unsuitable policies can lead to execution failures. Generalisation is particularly relevant when a robot has to deal with a large variety of objects and in different contexts. In this paper, we propose and analyse a strategy for generalising parameterised execution models of manipulation actions over different objects based on an object ontology. In particular, a robot transfers a known execution model to objects of related classes according to the ontology, but only if there is no other evidence that the model may be unsuitable. This allows using ontological knowledge as prior information that is then refined by the robot's own experiences. We verify our algorithm for two actions - grasping and stowing everyday objects - such that we show that the robot can deduce cases in which an existing policy can generalise to other objects and when additional execution knowledge has to be acquired.

【6】 Consensus-Informed Optimization Over Mixtures for Ambiguity-Aware Object SLAM 标题：模糊感知对象SLAM的混合一致性信息优化

作者：Ziqi Lu,Qiangqiang Huang,Kevin Doherty,John J. Leonard 机构：Massachusetts Institute of Technology (MIT) 链接：https://arxiv.org/abs/2107.09265 摘要：由于对称性、遮挡或知觉缺陷，在单次拍摄测量中，物体通常可能有多个可能的姿势。鲁棒的目标级同步定位与映射（object-SLAM）算法需要考虑姿态模糊。我们建议维持并随后消除多重姿态解释的歧义，以逐步恢复全球一致的世界代表性。最大混合模型被应用于隐式和有效地跟踪所有的姿势假设。通过提取时间一致性假设，将优化解引导到全局最优。这种一致性信息推理方法是在增量SLAM框架iSAM2的基础上，通过里程碑变量的重新初始化实现的。 摘要：Objects could often have multiple probable poses in single-shot measurements due to symmetry, occlusion or perceptual failures. A robust object-level simultaneous localization and mapping (object SLAM) algorithm needs to be aware of the pose ambiguity. We propose to maintain and subsequently dis-ambiguate the multiple pose interpretations to gradually recover a globally consistent world representation. The max-mixtures model is applied to implicitly and efficiently track all pose hypotheses. The temporally consistent hypotheses are extracted to guide the optimization solution into the global optimum. This consensus-informed inference method is implemented on top of the incremental SLAM framework iSAM2, via landmark variable re-initialization.

【7】 Attitude and In-orbit Residual Magnetic Moment Estimation of Small Satellites Using only Magnetometer 标题：仅用磁强计估算小卫星姿态和在轨剩余磁矩

作者：Raunak Srivastava,Roshan Sah,Kaushik Das 机构：TCS Research, Bangalore, India; + 备注：10 pages, 8 figures, Accepted in Small Satellite conference 2021 链接：https://arxiv.org/abs/2107.09257 摘要：姿态估计或确定是卫星保持有效运行的一项基本任务。由于星上空间和计算能力有限，这项任务在小型卫星上更为复杂。这一点，加上通常的低预算，限制了小卫星使用高精度传感器进行其特别重要的姿态估计任务。除此之外，由于小型卫星的尺寸和重量，与大型卫星相比，小型卫星对环境或轨道干扰更为敏感。在低地球轨道（LEO）的小卫星上，磁扰动是造成轨道扰动的主要因素。这种磁干扰依赖于卫星本身的剩余磁矩（RMM），为了获得更高的精度，必须实时测定。本文提出了一种利用随机游动模型进行卫星磁偶极子在轨估计的方法，以克服由于未知轨道磁扰动引起的误差。它还确保了偶极子以及卫星姿态估计只使用一个磁强计作为传感器。 摘要：Attitude estimation or determination is a fundamental task for satellites to remain effectively operational. This task is furthermore complicated on small satellites by the limited space and computational power available on-board. This, coupled with a usually low budget, restricts small satellites from using high precision sensors for its especially important task of attitude estimation. On top of this, small satellites, on account of their size and weight, are comparatively more sensitive to environmental or orbital disturbances as compared to their larger counterparts. Magnetic disturbance forms the major contributor to orbital disturbances on small satellites in Lower Earth Orbits (LEO). This magnetic disturbance depends on the Residual Magnetic Moment (RMM) of the satellite itself, which for higher accuracy should be determined in real-time. This paper presents a method for in-orbit estimation of the satellite magnetic dipole using a Random Walk Model in order to circumnavigate the inaccuracy arising due to unknown orbital magnetic disturbances. It is also ensured that the dipole as well as attitude estimation of the satellite is done using only a magnetometer as the sensor.

【8】 Constellation Design of Remote Sensing Small Satellite for Infrastructure Monitoring in India 标题：印度基础设施监测遥感小卫星星座设计

作者：Roshan Sah,Raunak Srivastava,Kaushik Das 机构：TCS Research, Bangalore, India; + 备注：10 Pages, 13 figure, Accepted for the Small Satellite Conference 2021 链接：https://arxiv.org/abs/2107.09253 摘要：利用合成孔径雷达有效载荷，为印度的基础设施监测开发了一个遥感小卫星星座系统。小卫星组成的低轨星座的设计方式可以覆盖整个印度。由于印度略高于赤道地区，因此调整轨道参数的方式考虑了倾斜36度和RAAN在600公里高度70-130度之间的变化。共设计了4个轨道面，每个轨道面由3颗120度真距平的小卫星组成。每颗卫星都能够拍摄多个外观图像，最小分辨率为每像素1米，测绘带宽度约为10公里。SAR有效载荷拍摄的多个外观图像有助于对我们感兴趣的印度足迹区域进行持续的基础设施监测。每颗小卫星都配备了使用X波段和VHF天线的通信有效载荷，而测控将使用高数据速率S波段发射机。本文只提出了一个覆盖指标的分析方法，我们设计的星座为我们的印度足迹，通过考虑重要的指标，如重访时间，响应时间和覆盖效率。结果表明，我们的星座平均重访时间约为15-35分钟，不到一个小时，这种迭代设计的星座平均响应时间约为25-120分钟，大部分时间覆盖率为100%。最后得出结论，每颗卫星的总质量为70公斤，研制成本约为75万美元。 摘要：A constellation of remote sensing small satellite system has been developed for infrastructure monitoring in India by using SAR Payload. The LEO constellation of the small satellites is designed in a way, which can cover the entire footprint of India. Since India lies a little above the equatorial region, the orbital parameters are adjusted in a way that inclination of 36 degrees and RAAN varies from 70-130 degrees at a height of 600 km has been considered. A total number of 4 orbital planes are designed in which each orbital plane consisting 3 small satellites with 120-degrees true anomaly separation. Each satellite is capable of taking multiple look images with the minimum resolution of 1 meter per pixel and swath width of 10 km approx. The multiple look images captured by the SAR payload help in continuous infrastructure monitoring of our interested footprint area in India. Each small satellite is equipped with a communication payload that uses X-band and VHF antenna, whereas the TT&C will use a high data-rate S-band transmitter. The paper presents only a coverage metrics analysis method of our designed constellation for our India footprint by considering the important metrics like revisit time, response time, and coverage efficiency. The result shows that the average revisits time for our constellation ranges from about 15- 35 min which is less than an hour and the average response time for this iteratively designed constellation ranges from about 25-120 min along with hundred percent coverage efficiency most of the time. Finally, it was concluded that each satellite has 70kg of total mass and costs around $ 0.75M to develop.

【9】 Reinforcement learning autonomously identifying the source of errors for agents in a group mission 标题：强化学习自主识别群体任务中Agent的误差源

作者：Keishu Utimula,Ken-taro Hayaschi,Kousuke Nakano,Kenta Hongo,Ryo Maezono 机构：School of Materials Science, JAIST, School of Information Science, Japan Advanced Institute of Science and Technology (JAIST), International School for Advanced Studies (SISSA), Via Bonomea , Trieste, Italy, Research Center for Advanced Computing Infrastructure 备注：4 pages, 1 figure 链接：https://arxiv.org/abs/2107.09232 摘要：当特工蜂拥而至执行任务时，指挥基地观察到的一些特工往往会突然失灵。通常很难区分故障是由执行器（假设，$h\u a$）还是传感器（假设，$h\u s$）引起的，仅通过命令库和相关代理之间的通信。通过与另一个代理发生碰撞，我们将能够区分哪种假设是可能的：对于$h\u a$，我们期望检测到相应的位移，而对于$h\u a$，我们没有。最好由人工智能（AI）自主生成这样的群体策略来掌握情况。区分的更好的行动（$，碰撞）将是那些最大化每个假设的预期行为之间的差异的行动，作为一个价值函数。然而，这样的行为只在整个可能性中非常稀少地存在，传统的基于梯度方法的搜索是没有意义的。相反，我们成功地应用了强化学习技术，实现了这种稀疏值函数的最大化。机器学习实际上是自主地归纳出碰撞行为来区分假设。通过动作识别出一个执行器出错的代理，这些代理的行为就像其他代理想要帮助发生故障的代理完成给定的任务一样。 摘要：When agents are swarmed to carry out a mission, there is often a sudden failure of some of the agents observed from the command base. It is generally difficult to distinguish whether the failure is caused by actuators (hypothesis, $h_a$) or sensors (hypothesis, $h_s$) solely by the communication between the command base and the concerning agent. By making a collision to the agent by another, we would be able to distinguish which hypothesis is likely: For $h_a$, we expect to detect corresponding displacements while for $h_a$ we do not. Such swarm strategies to grasp the situation are preferably to be generated autonomously by artificial intelligence (AI). Preferable actions ($e.g.$, the collision) for the distinction would be those maximizing the difference between the expected behaviors for each hypothesis, as a value function. Such actions exist, however, only very sparsely in the whole possibilities, for which the conventional search based on gradient methods does not make sense. Instead, we have successfully applied the reinforcement learning technique, achieving the maximization of such a sparse value function. The machine learning actually concluded autonomously the colliding action to distinguish the hypothesises. Getting recognized an agent with actuator error by the action, the agents behave as if other ones want to assist the malfunctioning one to achieve a given mission.

【10】 A Portable Agricultural Robot for Continuous Apparent Soil ElectricalConductivity Measurements to Improve Irrigation Practices 标题：一种可连续测量土壤表观电导率以改善灌溉方式的便携式农业机器人

作者：Merrick Campbell,Keran Ye,Elia Scudiero,Konstantinos Karydis 链接：https://arxiv.org/abs/2107.09219 摘要：近地遥感数据，如土壤表观电导率（ECa）的地理空间测量，被用于精确农业，以改进耕作方法和提高作物产量。近地传感器提供了有价值的信息，然而，收集、评估和解释测量数据的过程需要大量的人力。通过使用移动机器人自动化这一过程的一部分，可以帮助减轻劳动负担，提高数据收集的准确性和频率，并总体上增加对ECa测量技术的采用和使用。本文介绍了一种在微灌果园系统中自动进行地理空间ECa测量和绘制土壤含水量图的自动化方法。我们通过研究和考虑机器人身体对传感器读数的影响，用小型电磁感应传感器改造了一个小型轮式移动机器人，并开发了一个软件栈，以实现地理参考测量的自动记录。提出的机器人化ECa测量方法是通过将一个50m×30m的场与通过在同一场中行走传感器并沿着同一路径获得的人类传导测量基线进行映射来评估的。实验测试表明，尽管机器人的外形尺寸很小，但我们的方法产生的机器人化测量结果与人类进行的测量结果相当。 摘要：Near-ground sensing data, such as geospatial measurements of soil apparent electrical conductivity (ECa), are used in precision agriculture to improve farming practices and increase crop yield. Near-ground sensors provide valuable information, yet, the process of collecting, assessing, and interpreting measurements requires significant human labor. Automating parts of this process via the use of mobile robots can help decrease labor burden, and increase the accuracy and frequency of data collections, and overall increase the adoption and use of ECa measurement technology. This paper introduces a roboticized means to autonomously perform geospatial ECa measurements and map soil moisture content in micro-irrigated orchard systems. We retrofit a small wheeled mobile robot with a small electromagnetic induction sensor by studying and taking into consideration the effect of the robot body to the sensor's readings, and develop a software stack to enable autonomous logging of geo-referenced measurements. The proposed roboticized ECa measurement method is evaluated by mapping a 50m x 30m field against the baseline of human-conducted measurements obtained by walking the sensor in the same field and following the same path. Experimental testing reveals that our approach yields roboticized measurements comparable to human-conducted ones, despite the robot's small form factor.

【11】 DeepSocNav: Social Navigation by Imitating Human Behaviors 标题：DeepSocNav：模仿人类行为的社交导航

作者：Juan Pablo de Vicente,Alvaro Soto 备注：6 pages, Accepted paper at the RSS Workshop on Social Robot Navigation 2021 链接：https://arxiv.org/abs/2107.09170 摘要：当前用于训练社会行为的数据集通常是从监视应用程序中借用的，这些应用程序从鸟瞰的角度捕捉视觉数据。这就撇开了珍贵的关系和视觉线索，可以通过第一人称视角捕捉到一个场景。在这项工作中，我们提出了一个策略，利用现有的游戏引擎的力量，如统一，将现有的鸟瞰视图数据集转换成第一人称视图，特别是深度视图。使用这种策略，我们能够生成大量的合成数据，这些数据可以用来预先训练社交导航模型。为了验证我们的想法，我们提出了DeepSocNav，这是一个基于深度学习的模型，利用提出的方法生成合成数据。此外，DeepSocNav还包括一个作为辅助任务的自监督策略。这包括预测代理将面对的下一个深度帧。我们的实验表明，所提出的模型能够在社会导航得分方面优于相关基线。 摘要：Current datasets to train social behaviors are usually borrowed from surveillance applications that capture visual data from a bird's-eye perspective. This leaves aside precious relationships and visual cues that could be captured through a first-person view of a scene. In this work, we propose a strategy to exploit the power of current game engines, such as Unity, to transform pre-existing bird's-eye view datasets into a first-person view, in particular, a depth view. Using this strategy, we are able to generate large volumes of synthetic data that can be used to pre-train a social navigation model. To test our ideas, we present DeepSocNav, a deep learning based model that takes advantage of the proposed approach to generate synthetic data. Furthermore, DeepSocNav includes a self-supervised strategy that is included as an auxiliary task. This consists of predicting the next depth frame that the agent will face. Our experiments show the benefits of the proposed model that is able to outperform relevant baselines in terms of social navigation scores.