{"list":"other","total":58,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1711.07280","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","created":"2017-11-20","cited_by_count":1027},{"id":"1906.05797","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","created":"2019-06-13","cited_by_count":904},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"1808.10654","title":"Gibson Env: Real-World Perception for Embodied Agents","created":"2018-08-31","cited_by_count":481},{"id":"2007.00643","title":"Object Goal Navigation using Goal-Oriented Semantic Exploration","created":"2020-07-01","cited_by_count":429},{"id":"1609.05143","title":"Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning","created":"2016-09-16","cited_by_count":366},{"id":"1911.00357","title":"DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames","created":"2019-11-01","cited_by_count":362},{"id":"2004.05155","title":"Learning to Explore using Active Neural SLAM","created":"2020-04-10","cited_by_count":316},{"id":"1808.04355","title":"Large-Scale Study of Curiosity-Driven Learning","created":"2018-08-13","cited_by_count":280},{"id":"1906.04161","title":"Self-Supervised Exploration via Disagreement","created":"2019-06-10","cited_by_count":265},{"id":"2007.04954","title":"ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation","created":"2020-07-09","cited_by_count":250},{"id":"1702.03920","title":"Cognitive Mapping and Planning for Visual Navigation","created":"2017-02-13","cited_by_count":212},{"id":"1803.00653","title":"Semi-parametric Topological Memory for Navigation","created":"2018-03-01","cited_by_count":209},{"id":"2005.12256","title":"Neural Topological SLAM for Visual Navigation","created":"2020-05-25","cited_by_count":195},{"id":"1810.06543","title":"Visual Semantic Navigation using Scene Priors","created":"2018-10-15","cited_by_count":128},{"id":"1903.01959","title":"Learning Exploration Policies for Navigation","created":"2019-03-05","cited_by_count":116},{"id":"2012.05292","title":"Topological Planning with Transformers for Vision-and-Language Navigation","created":"2020-12-09","cited_by_count":116},{"id":"1903.03878","title":"Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks","created":"2019-03-09","cited_by_count":107},{"id":"2008.09285","title":"Occupancy Anticipation for Efficient Exploration and Navigation","created":"2020-08-21","cited_by_count":106},{"id":"2103.16544","title":"Visual Room Rearrangement","created":"2021-03-30","cited_by_count":102},{"id":"1912.11684","title":"Look, Listen, and Act: Towards Audio-Visual Embodied Navigation","created":"2019-12-25","cited_by_count":96},{"id":"2012.03912","title":"MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation","created":"2020-12-07","cited_by_count":95},{"id":"1603.02729","title":"Revisiting Active Perception","created":"2016-03-08","cited_by_count":94},{"id":"1805.06066","title":"Visual Representations for Semantic Target Driven Navigation","created":"2018-05-15","cited_by_count":89},{"id":"2012.11583","title":"Semantic Audio-Visual Navigation","created":"2020-12-21","cited_by_count":82},{"id":"2007.05655","title":"Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language Navigation","created":"2020-07-11","cited_by_count":71},{"id":"2008.09241","title":"Learning Affordance Landscapes for Interaction Exploration in 3D Environments","created":"2020-08-21","cited_by_count":65},{"id":"2103.14025","title":"The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AI","created":"2021-03-25","cited_by_count":65},{"id":"1702.08272","title":"A Dataset for Developing and Benchmarking Active Vision","created":"2017-02-27","cited_by_count":50},{"id":"2006.09367","title":"Semantic Curiosity for Active Visual Learning","created":"2020-06-16","cited_by_count":45},{"id":"2012.04512","title":"SSCNav: Confidence-Aware Semantic Scene Completion for Visual Semantic Navigation","created":"2020-12-08","cited_by_count":44},{"id":"2105.01060","title":"Curious Representation Learning for Embodied Intelligence","created":"2021-05-03","cited_by_count":44},{"id":"2007.03669","title":"See, Hear, Explore: Curiosity via Audio-Visual Association","created":"2020-07-07","cited_by_count":43},{"id":"1903.00445","title":"A Behavioral Approach to Visual Navigation with Graph Localization Networks","created":"2019-03-01","cited_by_count":40},{"id":"1709.00507","title":"Learning to Look Around: Intelligently Exploring Unseen Environments for Unknown Tasks","created":"2017-09-01","cited_by_count":38},{"id":"1909.12329","title":"Scaling Local Control to Large-Scale Topological Navigation","created":"2019-09-26","cited_by_count":37},{"id":"2105.07593","title":"Differentiable SLAM-net: Learning Particle SLAM for Visual Navigation","created":"2021-05-17","cited_by_count":34},{"id":"2007.05270","title":"Learning to plan with uncertain topological maps","created":"2020-07-10","cited_by_count":29},{"id":"1908.09073","title":"Situational Fusion of Visual Representation for Visual Navigation","created":"2019-08-24","cited_by_count":28},{"id":"2112.01010","title":"Differentiable Spatial Planning using Transformers","created":"2021-12-02","cited_by_count":25},{"id":"2105.00931","title":"GridToPix: Training Embodied Agents with Minimal Supervision","created":"2021-04-14","cited_by_count":21},{"id":"2012.09503","title":"Embodied Visual Active Learning for Semantic Segmentation","created":"2020-12-17","cited_by_count":19},{"id":"2110.05769","title":"Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents","created":"2021-10-12","cited_by_count":19},{"id":"1605.00164","title":"Look-ahead before you leap: end-to-end active recognition by forecasting the effect of motion","created":"2016-04-30","cited_by_count":18},{"id":"2107.06011","title":"Teaching Agents how to Map: Spatial Reasoning for Multi-Object Navigation","created":"2021-07-13","cited_by_count":17},{"id":"2207.03483","title":"Finding Fallen Objects Via Asynchronous Audio-Visual Integration","created":"2022-07-07","cited_by_count":14},{"id":"1807.11010","title":"Sidekick Policy Learning for Active Visual Exploration","created":"2018-07-29","cited_by_count":11},{"id":"2103.11374","title":"MaAST: Map Attention with Semantic Transformersfor Efficient Visual Navigation","created":"2021-03-21","cited_by_count":11},{"id":"2012.12142","title":"High-Speed Robot Navigation using Predicted Occupancy Maps","created":"2020-12-22","cited_by_count":10},{"id":"1910.08184","title":"Map-Predictive Motion Planning in Unknown Environments","created":"2019-10-17","cited_by_count":6},{"id":"2008.09622","title":"Learning to Set Waypoints for Audio-Visual Navigation","created":"2020-08-21","cited_by_count":5},{"id":"2011.03609","title":"A Few Shot Adaptation of Visual Navigation Skills to New Observations using Meta-Learning","created":"2020-11-06","cited_by_count":4},{"id":"2110.07171","title":"SGoLAM: Simultaneous Goal Localization and Mapping for Multi-Object Goal Navigation","created":"2021-10-14","cited_by_count":3},{"id":"2110.07184","title":"Self-Supervised Domain Adaptation for Visual Navigation with Global Map Consistency","created":"2021-10-14","cited_by_count":3}],"next_cursor":null}