The ability to autonomously explore and navigate a physical space is a fundamental requirement for virtually any mobile autonomous agent, from household robotic vacuums to autonomous vehicles. Traditional SLAM-based approaches for exploration and navigation largely focus on leveraging scene geometry, but fail to model dynamic objects (such as other agents) or semantic constraints (such as wet floors or doorways). Learning-based RL agents are an attractive alternative because they can incorporate both semantic and geometric information, but are notoriously sample inefficient, difficult to generalize to novel settings, and are difficult to interpret. In this paper, we combine the best of both worlds with a modular approach that learns a spatial representation of a scene that is trained to be effective when coupled with traditional geometric planners. Specifically, we design an agent that learns to predict a spatial affordance map that elucidates what parts of a scene are navigable through active self-supervised experience gathering. In contrast to most simulation environments that assume a static world, we evaluate our approach in the VizDoom simulator, using large-scale randomly-generated maps containing a variety of dynamic actors and hazards. We show that learned affordance maps can be used to augment traditional approaches for both exploration and navigation, providing significant improvements in performance.
Bielefeld University of Applied Sciences（比勒费尔德应用科技大学）；Bielefeld University（比勒费尔德大学）
The term "affordance" denotes the behavioral meaning of objects. We propose a cognitive architecture for the detection of affordances in the visual modality. This model is based on the internal simulation of movement sequences. For each movement step, the resulting sensory state is predicted by a forward model, which in turn triggers the generation of a new (simulated) motor command by an inverse model. Thus, a series of mental images in the sensory and in the motor domain is evoked. Starting from a real sensory state, a large number of such sequences is simulated in parallel. Final affordance…
Sapienza University of Rome（罗马第一大学）；University of Lincoln（林肯大学）
Affordances have been introduced in literature as action opportunities that objects offer, and used in robotics to semantically represent their interconnection. However, when considering an environment instead of an object, the problem becomes more complex due to the dynamism of its state. To tackle this issue, we introduce the concept of Spatio-Temporal Affordances (STA) and Spatio-Temporal Affordance Map (STAM). Using this formalism, we encode action semantics related to the environment to improve task execution capabilities of an autonomous robot. We experimentally validate our approach to …
Robotics, Perception and Learning Lab Royal Institute of Technology (KTH)（皇家理工学院（KTH）机器人、感知与学习实验室）
This paper studies the problem of detection and tracking of general objects with long-term dynamics, observed by a mobile robot moving in a large environment. A key problem is that due to the environment scale, it can only observe a subset of the objects at any given time. Since some time passes between observations of objects in different places, the objects might be moved when the robot is not there. We propose a model for this movement in which the objects typically only move locally, but with some small probability they jump longer distances, through what we call global motion. For filteri…
University of Liverpool（利物浦大学）；King’s College London（伦敦国王学院）；Monash University（莫纳什大学）
Transparent objects are widely used in our daily lives and therefore robots need to be able to handle them. However, transparent objects suffer from light reflection and refraction, which makes it challenging to obtain the accurate depth maps required to perform handling tasks. In this paper, we propose a novel affordance-based framework for depth reconstruction and manipulation of transparent objects, named A4T. A hierarchical AffordanceNet is first used to detect the transparent objects and their associated affordances that encode the relative positions of an object's different parts. Then, …
Human-robot handovers are characterized by high uncertainty and poor structure of the problem that make them difficult tasks. While machine learning methods have shown promising results, their application to problems with large state dimensionality, such as in the case of humanoid robots, is still limited. Additionally, by using these methods and during the interaction with the human operator, no guarantees can be obtained on the correct interpretation of spatial constraints (e.g., from social rules). In this paper, we present Policy Improvement with Spatio-Temporal Affordance Maps -- $π$-STAM…
Self-supervised grasp learning, i.e., learning to grasp by trial and error, has made great progress. However, it is still time-consuming to train such a model and also a challenge to apply it in practice. This work presents an accelerating method of robotic grasp learning via pretraining with coarse affordance maps of objects to be grasped based on a quite small dataset. A model generated through pre-training is harnessed as an initialization policy to warmly start grasp learning so as to guide a robot to capture more effective rewards at the beginning of training. An object in its coarse affo…
Robots need to understand their environment to perform their task. If it is possible to pre-program a visual scene analysis process in closed environments, robots operating in an open environment would benefit from the ability to learn it through their interaction with their environment. This ability furthermore opens the way to the acquisition of affordances maps in which the action capabilities of the robot structure its visual scene understanding. We propose an approach to build such affordances maps by relying on an interactive perception approach and an online classification. In the propo…
Avoiding obstacles in the perceived world has been the classical approach to autonomous mobile robot navigation. However, this usually leads to unnatural and inefficient motions that significantly differ from the way humans move in tight and dynamic spaces, as we do not refrain interacting with the environment around us when necessary. Inspired by this observation, we propose a framework for autonomous robot navigation among movable obstacles (NAMO) that is based on the theory of affordances and contact-implicit motion planning. We consider a realistic scenario in which a mobile service robot …
RoboAfford++: A Generative AI-Enhanced Dataset for Multimodal Affordance Learning in Robotic Manipulation and Navigation
Xiaomi EV（小米电动车）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学 Gallagher人工智能学院）；School of Computer Science and Information Engineering, Hefei University of Technology（合肥工业大学计算机科学与信息工程学院）
SurgAM: Surgical Affordance Map Prediction with Multimodal Feature Fusion for Robot Autonomy
Department of Computer Science and Engineering, The Chinese University of Hong Kong（香港中文大学计算机科学与工程系）；Department of Thoracic Surgery, Peking University People’s Hospital（北京大学人民医院胸外科）；Thoracic Oncology Institute, Peking University People’s Hospital（北京大学人民医院胸部肿瘤研究所）；Research Unit of Intelligence Diagnosis and Treatment in Early Non-small Cell Lung Cancer, Chinese Academy of Medical Sciences（中国医学科学院早期非小细胞肺癌智能诊断与治疗研究组）；Institute of Advanced Clinical Medicine, Peking University（北京大学先进临床医学院）；Beijing Key Laboratory of Innovative Application of Big Data in Lung Cancer, Peking University People’s Hospital（北京大学人民医院肺癌大数据创新应用北京市重点实验室）
Active Sensing Shapes Real-World Decision-Making through Dynamic Evidence Accumulation
The Hong Kong University of Science and Technology（香港科学与技术大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））；Civil and Environmental Engineering（土木与环境工程）；Emerging Interdisciplinary Area（新兴跨学科领域）；Systems Hub（系统枢纽）
osmAG-LLM: Zero-Shot Open-Vocabulary Object Navigation via Semantic Maps and Large Language Models Reasoning
Key Laboratory of Intelligent Perception and Human-Machine Collaboration – ShanghaiTech University, Ministry of Education, China（智能感知与人机协作重点实验室——上海科技大学，教育部，中国）；University of Bonn（波恩大学）；Lamarr Institute for ML and AI（Lamarr 人工智能与机器学习研究所）
San Francisco State University（旧金山州立大学）；Universidad de Los Andes（洛斯安第斯大学）
How do we move a robot efficiently from one position to another? To answer this question, we need to understand its configuration space, a 'map' where we can find every possible position of the robot. Unfortunately, these maps are very large, they live in high dimensions, and they are very difficult to visualize. Fortunately, for some discrete robots they are CAT(0) cubical complexes, a family of spaces with favorable properties. In this case, using ideas from combinatorics and geometric group theory, we can construct a 'remote control' to navigate these complicated maps, and move the robots o…
Berkeley AI Research (BAIR), University of California, Berkeley（加州大学伯克利分校伯克利人工智能研究中心（BAIR））
Mobile robot navigation is typically regarded as a geometric problem, in which the robot's objective is to perceive the geometry of the environment in order to plan collision-free paths towards a desired goal. However, a purely geometric view of the world can can be insufficient for many navigation problems. For example, a robot navigating based on geometry may avoid a field of tall grass because it believes it is untraversable, and will therefore fail to reach its desired goal. In this work, we investigate how to move beyond these purely geometric-based approaches using a method that learns a…
