PAPER Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation Vision-language navigation (VLN) is the task of navigating an embodied agent to carry out natural language instructions inside real 3D environments. In this paper, we study how to address three critical challenges for this task: the cross-modal grounding, arxiv.org 논문을 깊게 읽고 만든 자료가 아니므로, 참..
전체 글
PAPER Neural Modular Control for Embodied Question Answering We present a modular approach for learning policies for navigation over long planning horizons from language input. Our hierarchical policy operates at multiple timescales, where the higher-level master policy proposes subgoals to be executed by specialize arxiv.org 논문을 깊게 읽고 만든 자료가 아니므로, 참고만 해주세요. 얕은 지식으로 모델의 핵심 위주로만 파악한 자료이다 보니 없는 내용..
PAPER Look Before You Leap: Bridging Model-Free and Model-Based Reinforcement Learning for Planned-Ahead Vision-and-Language Navigatio Existing research studies on vision and language grounding for robot navigation focus on improving model-free deep reinforcement learning (DRL) models in synthetic environments. However, model-free DRL models do not consider the dynamics in the real-world arxiv.o..
PAPER Self-Monitoring Navigation Agent via Auxiliary Progress Estimation The Vision-and-Language Navigation (VLN) task entails an agent following navigational instruction in photo-realistic unknown environments. This challenging task demands that the agent be aware of which instruction was completed, which instruction is needed arxiv.org 논문을 깊게 읽고 만든 자료가 아니므로, 참고만 해주세요. 얕은 지식으로 모델의 핵심 위주로만 파악한 자..
PAPER Unified Pragmatic Models for Generating and Following Instructions We show that explicit pragmatic inference aids in correctly generating and following natural language instructions for complex, sequential tasks. Our pragmatics-enabled models reason about why speakers produce certain instructions, and about how listeners arxiv.org 논문을 깊게 읽고 만든 자료가 아니므로, 참고만 해주세요. 얕은 지식으로 모델의 핵심 위주로만 파악한 자료..
PAPER Integrating Algorithmic Planning and Deep Learning for Partially Observable Navigation We propose to take a novel approach to robot system design where each building block of a larger system is represented as a differentiable program, i.e. a deep neural network. This representation allows for integrating algorithmic planning and deep learnin arxiv.org 논문을 깊게 읽고 만든 자료가 아니므로, 참고만 해주세요. 얕은 지식..
PAPER QMDP-Net: Deep Learning for Planning under Partial Observability This paper introduces the QMDP-net, a neural network architecture for planning under partial observability. The QMDP-net combines the strengths of model-free learning and model-based planning. It is a recurrent policy network, but it represents a policy fo arxiv.org 논문을 깊게 읽고 만든 자료가 아니므로, 참고만 해주세요. 얕은 지식으로 모델의 핵심 위주로만 파악한 자료이..
PAPER FollowNet: Robot Navigation by Following Natural Language Directions with Deep Reinforcement Learning Understanding and following directions provided by humans can enable robots to navigate effectively in unknown situations. We present FollowNet, an end-to-end differentiable neural architecture for learning multi-modal navigation policies. FollowNet maps n arxiv.org 논문을 깊게 읽고 만든 자료가 아니므로, ..
PAPER Speaker-Follower Models for Vision-and-Language Navigation Navigation guided by natural language instructions presents a challenging reasoning problem for instruction followers. Natural language instructions typically identify only a few high-level decisions and landmarks rather than complete low-level motor behav arxiv.org 논문을 깊게 읽고 만든 자료가 아니므로, 참고만 해주세요. 얕은 지식으로 모델의 핵심 위주로만 파악한 자료이다 보니 없..
PAPER Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments A robot that can carry out a natural-language instruction has been a dream since before the Jetsons cartoon series imagined a life of leisure mediated by a fleet of attentive robot helpers. It is a dream that remains stubbornly distant. However, recent adv arxiv.org Challenge & Data ..
