Navigating the world is a fundamental ability for any living entity. Accomplishing the same degree of freedom in technology has proven to be difficult. The brain is the only known mechanism capable of voluntary navigation, making neuroscience our best source of inspiration toward autonomy. Assuming that state representation is key, we explore the difference in how the brain and the machine represent the navigational state. Where Reinforcement Learning (RL) requires a monolithic state representation in accordance with the Markov property, Neural Representation of Euclidean Space (NRES) reflects navigational state via distributed activation patterns. We show how NRES-Oriented RL (neoRL) agents are possible before verifying our theoretical findings by experiments. Ultimately, neoRL agents are capable of behavior synthesis across state spaces -- allowing for decomposition of the problem into smaller spaces, alleviating the curse of dimensionality.
UiT - The Arctic University of Norway（特罗姆瑟大学-挪威北极圈大学）
Edward C. Tolman found reinforcement learning unsatisfactory for explaining intelligence and proposed a clear distinction between learning and behavior. Tolman's ideas on latent learning and cognitive maps eventually led to what is now known as conceptual space, a geometric representation where concepts and ideas can form points or shapes.Active navigation between ideas - reasoning - can be expressed directly as purposive navigation in conceptual space. Assimilating the theory of conceptual space from modern neuroscience, we propose autonomous navigation as a valid approach for emulated cognit…
We present SGoLAM, short for simultaneous goal localization and mapping, which is a simple and efficient algorithm for Multi-Object Goal navigation. Given an agent equipped with an RGB-D camera and a GPS/Compass sensor, our objective is to have the agent navigate to a sequence of target objects in realistic 3D environments. Our pipeline fully leverages the strength of classical approaches for visual navigation, by decomposing the problem into two key components: mapping and goal localization. The mapping module converts the depth observations into an occupancy map, and the goal localization mo…
Shanghai Jiao Tong University（上海交通大学）；Xinjiang University of Finance and Economics（新疆财经大学）；Shenzhen University（深圳大学）；Southern University of Science and Technology（南方科技大学）
LaViRA: Language-Vision-Robot Actions Translation for Zero-Shot Vision Language Navigation in Continuous Environments
School of Computer Science, Nanjing University（南京大学计算机科学学院）；School of Intelligence Science and Technology, Nanjing University（南京大学智能科学与技术学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Simon Fraser University（西蒙弗雷泽大学）；University of Southern California（南加州大学）；Princeton University（普林斯顿大学）；Google Research（谷歌研究院）
Learning to follow instructions is of fundamental importance to autonomous agents for vision-and-language navigation (VLN). In this paper, we study how an agent can navigate long paths when learning from a corpus that consists of shorter ones. We show that existing state-of-the-art agents do not generalize well. To this end, we propose BabyWalk, a new VLN agent that is learned to navigate by decomposing long instructions into shorter ones (BabySteps) and completing them sequentially. A special design memory buffer is used by the agent to turn its past experiences into contexts for future steps…
Moscow Institute of Physics and Technology（莫斯科物理技术学院）；Federal Research Center “Computer Science and Control” of the Russian Academy of Sciences（俄罗斯科学院“计算机科学与控制”联邦研究中心）
Deep Learning has revolutionized our ability to solve complex problems such as Vision-and-Language Navigation (VLN). This task requires the agent to navigate to a goal purely based on visual sensory inputs given natural language instructions. However, prior works formulate the problem as a navigation graph with a discrete action space. In this work, we lift the agent off the navigation graph and propose a more complex VLN setting in continuous 3D reconstructed environments. Our proposed setting, Robo-VLN, more closely mimics the challenges of real world navigation. Robo-VLN tasks have longer t…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
This paper investigates the automatic exploration problem under the unknown environment, which is the key point of applying the robotic system to some social tasks. The solution to this problem via stacking decision rules is impossible to cover various environments and sensor properties. Learning based control methods are adaptive for these scenarios. However, these methods are damaged by low learning efficiency and awkward transferability from simulation to reality. In this paper, we construct a general exploration framework via decomposing the exploration process into the decision, planning,…
WMNav: Integrating Vision-Language Models into World Models for Object Goal Navigation
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Computer Science, Wuhan University（武汉大学计算机学院）；School of Computer Science, University of Technology Sydney（悉尼大学计算机学院）；IAIR, Xi’an Jiaotong University（西安交通大学IAIR）
