Modern reinforcement learning algorithms can learn solutions to increasingly difficult control problems while at the same time reduce the amount of prior knowledge needed for their application. One of the remaining challenges is the definition of reward schemes that appropriately facilitate exploration without biasing the solution in undesirable ways, and that can be implemented on real robotic systems without expensive instrumentation. In this paper we focus on a setting in which goal tasks are defined via simple sparse rewards, and exploration is facilitated via agent-internal auxiliary tasks. We introduce the idea of simple sensor intentions (SSIs) as a generic way to define auxiliary tasks. SSIs reduce the amount of prior knowledge that is required to define suitable rewards. They can further be computed directly from raw sensor streams and thus do not require expensive and possibly brittle state estimation on real systems. We demonstrate that a learning system based on these rewards can solve complex robotic tasks in simulation and in real world settings. In particular, we show that a real robotic arm can learn to grasp and lift and solve a Ball-in-a-Cup task from scratch, when only raw sensor streams are used for both controller input and in the auxiliary reward definition.
Sensorium Arc: AI Agent System for Oceanic Data Exploration and Interactive Eco-Art
Immersive Media Design University of Maryland College Park（沉浸媒体设计大学马里兰大学学院公园分校）；Center for the Study of the Force Majeure University of California, Santa Cruz（重大研究机构加州大学圣克鲁兹分校）；Virtual Planet Technologies（虚拟星球技术）
Efficient exploration is a long-standing problem in reinforcement learning since extrinsic rewards are usually sparse or missing. A popular solution to this issue is to feed an agent with novelty signals as intrinsic rewards. In this work, we introduce SEMI, a self-supervised exploration policy by incentivizing the agent to maximize a new novelty signal: multisensory incongruity, which can be measured in two aspects, perception incongruity and action incongruity. The former represents the misalignment of the multisensory inputs, while the latter represents the variance of an agent's policies u…
Reinforcement Learning (RL) is known to be often unsuccessful in environments with sparse extrinsic rewards. A possible countermeasure is to endow RL agents with an intrinsic reward function, or 'intrinsic motivation', which rewards the agent based on certain features of the current sensor state. An intrinsic reward function based on the principle of empowerment assigns rewards proportional to the amount of control the agent has over its own sensors. We implemented a variation on a recently proposed intrinsically motivated agent, which we refer to as the 'curious' agent, and an empowerment-ins…
Uber Advanced Technologies Group（优步先进技术集团）；University of Toronto（多伦多大学）
In order to plan a safe maneuver, self-driving vehicles need to understand the intent of other traffic participants. We define intent as a combination of discrete high-level behaviors as well as continuous trajectories describing future motion. In this paper, we develop a one-stage detector and forecaster that exploits both 3D point clouds produced by a LiDAR sensor as well as dynamic maps of the environment. Our multi-task model achieves better accuracy than the respective separate modules while saving computation, which is critical to reducing reaction time in self-driving applications.
Artificial intelligence (AI) agents will need to interact with both other AI agents and humans. Creating models of associates help to predict the modeled agents' actions, plans, and intentions. This work introduces algorithms that predict actions, plans and intentions in repeated play games, with providing an exploration of algorithms. We form a generative Bayesian approach to model S#. S# is designed as a robust algorithm that learns to cooperate with its associate in 2 by 2 matrix games. The actions, plans and intentions associated with each S# expert are identified from the literature, grou…
City University of Hong Kong（香港城市大学）；Hong Kong University of Science and Technology（香港科技大学）
Exploration in an unknown environment is the core functionality for mobile robots. Learning-based exploration methods, including convolutional neural networks, provide excellent strategies without human-designed logic for the feature extraction. But the conventional supervised learning algorithms cost lots of efforts on the labeling work of datasets inevitably. Scenes not included in the training set are mostly unrecognized either. We propose a deep reinforcement learning method for the exploration of mobile robots in an indoor environment with the depth information from an RGB-D sensor only. …
Sound is one of the most informative and abundant modalities in the real world while being robust to sense without contacts by small and cheap sensors that can be placed on mobile devices. Although deep learning is capable of extracting information from multiple sensory inputs, there has been little use of sound for the control and learning of robotic actions. For unsupervised reinforcement learning, an agent is expected to actively collect experiences and jointly learn representations and policies in a self-supervised way. We build realistic robotic manipulation scenarios with physics-based s…
General AI Lab（通用人工智能实验室）；Horizon Robotics Inc.（地平线机器人技术有限公司）
Standard model-free reinforcement learning algorithms optimize a policy that generates the action to be taken in the current time step in order to maximize expected future return. While flexible, it faces difficulties arising from the inefficient exploration due to its single step nature. In this work, we present Generative Planning method (GPM), which can generate actions not only for the current step, but also for a number of future steps (thus termed as generative planning). This brings several benefits to GPM. Firstly, since GPM is trained by maximizing value, the plans generated from it c…
Proactively perceiving others' intentions is a crucial skill to effectively interact in unstructured, dynamic and novel environments. This work proposes a first step towards embedding this skill in support robots for search and rescue missions. Predicting the responders' intentions, indeed, will enable exploration approaches which will identify and prioritise areas that are more relevant for the responder and, thus, for the task, leading to the development of safer, more robust and efficient joint exploration strategies. More specifically, this paper presents an active intention recognition pa…
Inspired by the human ability to perform complex manipulation in the complete absence of vision (like retrieving an object from a pocket), the robotic manipulation field is motivated to develop new methods for tactile-based object interaction. However, tactile sensing presents the challenge of being an active sensing modality: a touch sensor provides sparse, local data, and must be used in conjunction with effective exploration strategies in order to collect information. In this work, we focus on the process of guiding tactile exploration, and its interplay with task-related decision making. W…
Zurich University of Applied Sciences（苏黎世应用科学大学）；Politecnico di Torino（都灵理工大学）；TOELT LLC（TOELT有限责任公司）；SCA San Sebastián Puente del Ventorro（圣塞巴斯蒂安蓬特德尔文托罗农业合作社）
Extra virgin olive oil (EVOO) is the highest quality of olive oil and is characterized by highly beneficial nutritional properties. The large increase in both consumption and fraud, for example through adulteration, creates new challenges and an increasing demand for developing new quality assessment methodologies that are easier and cheaper to perform. As of today, the determination of olive oil quality is performed by producers through chemical analysis and organoleptic evaluation. The chemical analysis requires the advanced equipment and chemical knowledge of certified laboratories, and has…
Delft University of Technology（代尔夫特理工大学）；Almende B.V.（Almende公司）
This paper discusses various techniques to let an agent learn how to predict the effects of its own actions on its sensor data autonomously, and their usefulness to apply them to visual sensors. An Extreme Learning Machine is used for visuomotor prediction, while various autonomous control techniques that can aid the prediction process by balancing exploration and exploitation are discussed and tested in a simple system: a camera moving over a 2D greyscale image.
Mind2Drive: Predicting Driver Intentions from EEG in Real-world On-Road Driving
Department of Computer Science, Imam Mohammad Ibn Saud Islamic University（伊玛姆·莫哈默德·伊本·沙特伊斯兰大学计算机科学系）；Department of Computer Science, Princess Nourah bint Abdulrahman University（努拉·本·阿卜杜勒拉赫曼大学计算机科学系）
The technological advancement in data analysis and sensor technology has contributed to a growth in knowledge of the surrounding environments. Feng Shui, the Chinese philosophy of evaluating a certain environment and how it influences human well-being, can only be determined by self-claimed specialists for the past thousands of years. We developed a device as well as a procedure to evaluate the ambient environment of a room to perform a study that attempts to use sensor data to predict the well-being score of a person in that environment, therefore evaluating the primary aspect of Feng Shui. O…
Oden Institute for Computational Engineering and Sciences（奥登计算工程与科学研究所）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）
We consider the exploration problem: an agent equipped with a depth sensor must map out a previously unknown environment using as few sensor measurements as possible. We propose an approach based on supervised learning of a greedy algorithm. We provide a bound on the optimality of the greedy algorithm using submodularity theory. Using a level set representation, we train a convolutional neural network to determine vantage points that maximize visibility. We show that this method drastically reduces the on-line computational cost and determines a small set of vantage points that solve the probl…
The University of Nottingham, Malaysia Campus（诺丁汉大学马来西亚校区）
The pipelines transmission system is one of the growing aspects, which has existed for a long time in the energy industry. The cost of in-pipe exploration for maintaining service always draws lots of attention in this industry. Normally exploration methods (e.g. Magnetic flux leakage and eddy current) will establish the sensors stationary for each pipe milestone or carry sensors to travel inside the pipe. It makes the maintenance process very difficult due to the massive amount of sensors. One of the solutions is to implement machine learning techniques for the analysis of sensory data. Althou…
