ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation [PDF]
International Conference on Machine Learning, 2023 The ability to accurately locate and navigate to a specific object is a crucial capability for embodied agents that operate in the real world and interact with objects to complete tasks.
KAI-QING Zhou +6 more
semanticscholar +1 more source
NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration [PDF]
IEEE International Conference on Robotics and Automation, 2023 Robotic learning for navigation in unfamiliar environments needs to provide policies for both task-oriented navigation (i.e., reaching a goal that the robot has located), and task-agnostic exploration (i.e., searching for a goal in a novel setting ...
A. Sridhar +3 more
semanticscholar +1 more source
ANYmal parkour: Learning agile navigation for quadrupedal robots [PDF]
Science Robotics, 2023 Performing agile navigation with four-legged robots is a challenging task because of the highly dynamic motions, contacts with various parts of the robot, and the limited field of view of the perception sensors.
David Hoeller +3 more
semanticscholar +1 more source
NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models [PDF]
AAAI Conference on Artificial Intelligence, 2023 Trained with an unprecedented scale of data, large language models (LLMs) like ChatGPT and GPT-4 exhibit the emergence of significant reasoning abilities from model scaling.
Gengze Zhou, Yicong Hong, Qi Wu
semanticscholar +1 more source
ViNT: A Foundation Model for Visual Navigation [PDF]
Conference on Robot Learning, 2023 General-purpose pre-trained models ("foundation models") have enabled practitioners to produce generalizable solutions for individual machine learning problems with datasets that are significantly smaller than those required for learning from scratch ...
Dhruv Shah +6 more
semanticscholar +1 more source
Visual Language Maps for Robot Navigation [PDF]
IEEE International Conference on Robotics and Automation, 2022 Grounding language to the visual observations of a navigating agent can be performed using off-the-shelf visual-language models pretrained on Internet-scale data (e.g., image captions).
Chen Huang +3 more
semanticscholar +1 more source
System of automatic generation of ship maneuver documentation [PDF]
Archives of Transport, 2023 According to the definition in the resolution International Maritime Organization no A.860 (IMO 1997) navigation is the process of planning, recording, and controlling the movement of a craft from one place to another.
Piotr Zwolan +4 more
doaj +1 more source
ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023 Vision-language navigation is a task that requires an agent to follow instructions to navigate in environments. It becomes increasingly crucial in the field of embodied AI, with potential applications in autonomous navigation, search and rescue, and ...
Dongyan An +6 more
semanticscholar +1 more source
CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation [PDF]
Computer Vision and Pattern Recognition, 2022 For robots to be generally useful, they must be able to find arbitrary objects described by people (i.e., be language-driven) even without expensive navigation training on in-domain data (i.e., perform zero-shot inference).
S. Gadre +4 more
semanticscholar +1 more source
LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action [PDF]
Conference on Robot Learning, 2022 Goal-conditioned policies for robotic navigation can be trained on large, unannotated datasets, providing for good generalization to real-world settings.
Dhruv Shah +3 more
semanticscholar +1 more source