{"list":"other","total":52,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2109.08238","title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","created":"2021-09-16","cited_by_count":592},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"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":"1905.06113","title":"Human Motion Trajectory Prediction: A Survey","created":"2019-05-15","cited_by_count":232},{"id":"2310.13724","title":"Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots","created":"2023-10-19","cited_by_count":228},{"id":"1611.03673","title":"Learning to Navigate in Complex Environments","created":"2016-11-11","cited_by_count":198},{"id":"2301.04926","title":"CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP","created":"2023-01-12","cited_by_count":181},{"id":"1809.08835","title":"Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning","created":"2018-09-24","cited_by_count":175},{"id":"1703.08862","title":"Socially Aware Motion Planning with Deep Reinforcement Learning","created":"2017-03-26","cited_by_count":136},{"id":"2303.17597","title":"Robo3D: Towards Robust and Reliable 3D Perception against Corruptions","created":"2023-03-30","cited_by_count":129},{"id":"2501.04003","title":"Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives","created":"2025-01-07","cited_by_count":122},{"id":"1902.03748","title":"Peeking into the Future: Predicting Future Person Activities and Locations in Videos","created":"2019-02-11","cited_by_count":114},{"id":"2103.05668","title":"Core Challenges of Social Robot Navigation: A Survey","created":"2021-03-09","cited_by_count":106},{"id":"1505.01596","title":"Learning to See by Moving","created":"2015-05-07","cited_by_count":102},{"id":"1910.14442","title":"Interactive Gibson Benchmark (iGibson 0.5): A Benchmark for Interactive Navigation in Cluttered Environments","created":"2019-10-30","cited_by_count":90},{"id":"1912.06445","title":"The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction","created":"2019-12-13","cited_by_count":72},{"id":"2412.04383","title":"SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding","created":"2024-12-05","cited_by_count":67},{"id":"2509.07996","title":"3D and 4D World Modeling: A Survey","created":"2025-09-04","cited_by_count":67},{"id":"2502.13451","title":"MapNav: A Novel Memory Representation via Annotated Semantic Maps for Vision-and-Language Navigation","created":"2025-02-19","cited_by_count":60},{"id":"2306.16740","title":"Principles and Guidelines for Evaluating Social Robot Navigation Algorithms","created":"2023-06-29","cited_by_count":56},{"id":"2505.09577","title":"VTLA: Vision-Tactile-Language-Action Model with Preference Learning for Insertion Manipulation","created":"2025-05-14","cited_by_count":55},{"id":"2306.03899","title":"Towards Label-free Scene Understanding by Vision Foundation Models","created":"2023-06-06","cited_by_count":54},{"id":"2310.15171","title":"RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions","created":"2023-10-23","cited_by_count":49},{"id":"2304.06719","title":"RoboBEV: Towards Robust Bird's Eye View Perception under Corruptions","created":"2023-04-13","cited_by_count":42},{"id":"2311.12751","title":"Towards Natural Language-Guided Drones: GeoText-1652 Benchmark with Spatial Relation Matching","created":"2023-11-21","cited_by_count":42},{"id":"2405.17426","title":"Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Driving","created":"2024-05-27","cited_by_count":41},{"id":"2311.06922","title":"A Survey on Socially Aware Robot Navigation: Taxonomy and Future Challenges","created":"2023-11-12","cited_by_count":39},{"id":"1909.04403","title":"TH\\\"OR: Human-Robot Navigation Data Collection and Accurate Motion Trajectories Dataset","created":"2019-09-10","cited_by_count":36},{"id":"2010.08600","title":"Robot Navigation in Constrained Pedestrian Environments using Reinforcement Learning","created":"2020-10-16","cited_by_count":30},{"id":"2406.12214","title":"Is Your HD Map Constructor Reliable under Sensor Corruptions?","created":"2024-06-18","cited_by_count":28},{"id":"2403.17009","title":"Is Your LiDAR Placement Optimized for 3D Scene Understanding?","created":"2024-03-25","cited_by_count":26},{"id":"2403.15223","title":"TriHelper: Zero-Shot Object Navigation with Dynamic Assistance","created":"2024-03-22","cited_by_count":25},{"id":"2106.11650","title":"A Survey on Human-aware Robot Navigation","created":"2021-06-22","cited_by_count":24},{"id":"2405.08816","title":"The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition","created":"2024-05-14","cited_by_count":23},{"id":"2009.05702","title":"Risk-Sensitive Sequential Action Control with Multi-Modal Human Trajectory Forecasting for Safe Crowd-Robot Interaction","created":"2020-09-12","cited_by_count":21},{"id":"2502.04377","title":"MapFusion: A Novel BEV Feature Fusion Network for Multi-modal Map Construction","created":"2025-02-05","cited_by_count":21},{"id":"2503.00778","title":"AffordGrasp: In-Context Affordance Reasoning for Open-Vocabulary Task-Oriented Grasping in Clutter","created":"2025-03-02","cited_by_count":20},{"id":"2507.17665","title":"Perspective-Invariant 3D Object Detection","created":"2025-07-23","cited_by_count":18},{"id":"2309.15234","title":"Multi-Robot Cooperative Socially-Aware Navigation Using Multi-Agent Reinforcement Learning","created":"2023-09-26","cited_by_count":17},{"id":"1609.06838","title":"Deep-Learned Collision Avoidance Policy for Distributed Multi-Agent Navigation","created":"2016-09-22","cited_by_count":15},{"id":"2507.00861","title":"SafeMap: Robust HD Map Construction from Incomplete Observations","created":"2025-07-01","cited_by_count":14},{"id":"2508.04598","title":"$NavA^3$: Understanding Any Instruction, Navigating Anywhere, Finding Anything","created":"2025-08-06","cited_by_count":14},{"id":"2307.15061","title":"The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation","created":"2023-07-27","cited_by_count":13},{"id":"2409.10906","title":"Multi-Floor Zero-Shot Object Navigation Policy","created":"2024-09-17","cited_by_count":12},{"id":"2501.04005","title":"LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Driving","created":"2025-01-07","cited_by_count":12},{"id":"2409.13244","title":"From Cognition to Precognition: A Future-Aware Framework for Social Navigation","created":"2024-09-20","cited_by_count":10},{"id":"2306.11377","title":"HabiCrowd: A High Performance Simulator for Crowd-Aware Visual Navigation","created":"2023-06-20","cited_by_count":9},{"id":"2403.00991","title":"SELFI: Autonomous Self-Improvement with Reinforcement Learning for Social Navigation","created":"2024-03-01","cited_by_count":8},{"id":"2507.05260","title":"Beyond One Shot, Beyond One Perspective: Cross-View and Long-Horizon Distillation for Better LiDAR Representations","created":"2025-07-07","cited_by_count":7},{"id":"2212.00767","title":"Exploiting Proximity-Aware Tasks for Embodied Social Navigation","created":"2022-12-01","cited_by_count":6},{"id":"2304.14102","title":"SocNavGym: A Reinforcement Learning Gym for Social Navigation","created":"2023-04-27","cited_by_count":3}],"next_cursor":null}