On the Emergence of Symmetrical Reality
Not on the map. Why?
Abstract (arXiv)
Artificial intelligence (AI) has revolutionized human cognitive abilities and facilitated the development of new AI entities capable of interacting with humans in both physical and virtual environments. Despite the existence of virtual reality, mixed reality, and augmented reality for several years, integrating these technical fields remains a formidable challenge due to their disparate application directions. The advent of AI agents, capable of autonomous perception and action, further compounds this issue by exposing the limitations of traditional human-centered research approaches. It is imperative to establish a comprehensive framework that accommodates the dual perceptual centers of humans and AI agents in both physical and virtual worlds. In this paper, we introduce the symmetrical reality framework, which offers a unified representation encompassing various forms of physical-virtual amalgamations. This framework enables researchers to better comprehend how AI agents can collaborate with humans and how distinct technical pathways of physical-virtual integration can be consolidated from a broader perspective. We then delve into the coexistence of humans and AI, demonstrating a prototype system that exemplifies the operation of symmetrical reality systems for specific tasks, such as pouring water. Subsequently, we propose an instance of an AI-driven active assistance service that illustrates the potential applications of symmetrical reality. This paper aims to offer beneficial perspectives and guidance for researchers and practitioners in different fields, thus contributing to the ongoing research about human-AI coexistence in both physical and virtual environments.
Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 40 of its 152 references that are in the map. First posted on arXiv 26 Jan 2024.
Builds on
40 of 152 references.
References · 40
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2023GPT-4 Technical Reportcited by 18,396
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
- 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
- 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
- 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
- 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
- 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
- 2019Habitat: A Platform for Embodied AI Researchcited by 1,191
- 2017AI2-THOR: An Interactive 3D Environment for Visual AIcited by 869
28 more
- 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 595
- 2018VirtualHome: Simulating Household Activities via Programscited by 415
- 2016Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learningcited by 366
- 2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 365
- 2017Embodied Question Answeringcited by 336
- 2020Neural Additive Models: Interpretable Machine Learning with Neural Netscited by 319
- 2017Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperationcited by 289
- 2021A Survey of Embodied AI: From Simulators to Research Taskscited by 261
- 2020Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Surveycited by 254
- 2020ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulationcited by 250
- 2016Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?cited by 194
- 2020iGibson 1.0: a Simulation Environment for Interactive Tasks in Large Realistic Scenescited by 155
- 2019Global Explanations of Neural Networks: Mapping the Landscape of Predictionscited by 32
- 2021Towards Relatable Explainable AI with the Perceptual Processcited by 27
- 2017Baxter's Homunculus: Virtual Reality Spaces for Teleoperation in Manufacturingcited by 19
- 2020Joint Mind Modeling for Explanation Generation in Complex Human-Robot Collaborative Taskscited by 15
- 2020Human-Robot Interaction in a Shared Augmented Reality Workspacecited by 10
- 2017Brain Intelligence: Go Beyond Artificial Intelligencecited by 9
- 2017AI Challenges in Human-Robot Cognitive Teamingcited by 9
- 2019VRGym: A Virtual Testbed for Physical and Interactive AIcited by 9
- 2021eXtended Artificial Intelligence: New Prospects of Human-AI Interaction Researchcited by 6
- 2019Symmetrical Reality: Toward a Unified Framework for Physical and Virtual Realitycited by 4
- 2021Show Me What You Can Do: Capability Calibration on Reachable Workspace for Human-Robot Collaborationcited by 4
- 2016Feedback Motion Planning for Liquid Transfer using Supervised Learningcited by 3
- 2018Augmented Artificial Intelligence: a Conceptual Frameworkcited by 3
- 2018Inverse Augmented Reality: A Virtual Agent's Perspectivecited by 3
- 2021Extended Reality (XR) Remote Research: a Survey of Drawbacks and Opportunitiescited by 3
- 2018All Reality: Virtual, Augmented, Mixed (X), Mediated (X,Y), and Multimediated Realitycited by 2
Built on by
Citing papers per year: 2025: 4; 2026: 4.
8 papers.
- 2025TongSIM: A General Platform for Simulating Intelligent Machinescited by 4
- 2026Learning What Matters Now: Dynamic Preference Inference under Contextual Shiftscited by 1
- 2025Body Discovery of Embodied AIcited by 0
- 2025Learning Long Short-Term Intention within Human Daily Behaviorscited by 0
- 2025S3IT: A Benchmark for Spatially Situated Social Intelligence Testcited by 0
- 2026Exploring Human-Machine Coexistence in Symmetrical Realitycited by 0
- 2026TeachAnything: A Multimodal Crowdsourcing Platform for Training Embodied AI Agents in Symmetrical Realitycited by 0
- 2026BotDirector: Robot Storytelling Across the Symmetrical Reality with Multi-modal Interactionscited by 0
- 2026BotDirector: Robot Storytelling Across the Symmetrical Reality with Multi-modal Interactions2 Jun 2026
- 2026TeachAnything: A Multimodal Crowdsourcing Platform for Training Embodied AI Agents in Symmetrical Reality14 May 2026
- 2026Learning What Matters Now: Dynamic Preference Inference under Contextual Shifts24 Mar 2026
- 2026Exploring Human-Machine Coexistence in Symmetrical Reality25 Feb 2026
- 2025TongSIM: A General Platform for Simulating Intelligent Machines23 Dec 2025
- 2025S3IT: A Benchmark for Spatially Situated Social Intelligence Test23 Dec 2025
- 2025Learning Long Short-Term Intention within Human Daily Behaviors10 Apr 2025
- 2025Body Discovery of Embodied AI25 Mar 2025