Browse State-of-the-Art › PointGoal Navigation
PointGoal Navigation
15 papers with code · 1 benchmark · 2 datasets archive 2025-07-28
Point goal navigation is a task where an agent navigates to a specific location, defined by coordinates (x, y), in an environment using sensory inputs like vision or depth, without a pre-built map, relying on real-time perception and decision-making.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
1 leaderboard table shown for this task, 1 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| Gibson PointGoal Navigation (2 rows) | Depth DDPPO | DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
2 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 25 · with a code link: 15 · where Syntology ran a sample: 4 (3 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (4 of 25 tagged: 3 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 25 of 25, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from.
-
2 Apr 2019 13 repositories listed Syntology community repositories only · 13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 1 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 15 harvested samples) · 15 pointer-only (licence)We present Habitat, a platform for research in embodied artificial intelligence (AI).
-
1 Nov 2019 8 repositories listedWe leverage this scaling to train an agent for 2.
-
13 Dec 2019 4 repositories listed Syntology 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples)Second, we investigate the sim2real predictivity of Habitat-Sim for PointGoal navigation.
-
16 Sep 2021 3 repositories listed Syntology official: harvested, nothing ran · 0 ran · 2 unverified (of 2 harvested samples) · 2 pointer-only (licence)When compared to existing photorealistic 3D datasets such as Replica, MP3D, Gibson, and ScanNet, images rendered from HM3D have 20 - 85% higher visual fidelity w. r. t.
-
10 Apr 2020 2 repositories listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample)The use of learning provides flexibility with respect to input modalities (in the SLAM module), leverages structural regularities of the world (in global policies), and provides robustness to errors in state estimation…
-
17 Dec 2022 1 repository listedIn this work, we compare the state-of-the-art Deep Reinforcement Learning based approaches with Partially Observable Markov Decision Process (POMDP) formulation of the point goal navigation problem.
-
11 Oct 2022 1 repository listedSpecifically, the Pick skill involves a robot picking an object from a table.
-
2 Jun 2022 1 repository listedHowever, for PointNav in a realistic setting (RGB-D and actuation noise, no GPS+Compass), this is an open question; one we tackle in this paper.
-
19 Apr 2022 1 repository listedThis feature is challenging for occupancy-based agents which are usually trained in crowded domestic environments with plenty of occupancy information.
-
2 Feb 2022 1 repository listedAll the proposed navigation models have been trained with the Habitat simulator on a synthetic office environment and have been tested on the same real-world environment using a real robotic platform.
-
17 Sep 2021 1 repository listedUnder this setting, the agent incurs a penalty for using this privileged information, encouraging the agent to only leverage this information when it is crucial to learning.
-
12 May 2021 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 7 harvested samples)In this work, we detail how to transfer the knowledge acquired in simulation into the real world.
-
12 Mar 2021 1 repository listedWe accelerate deep reinforcement learning-based training in visually complex 3D environments by two orders of magnitude over prior work, realizing end-to-end training speeds of over 19, 000 frames of experience per…
-
9 Jul 2020 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)PointGoal Navigation is an embodied task that requires agents to navigate to a specified point in an unseen environment.
-
8 Jan 2020 1 repository listedIn this paper, we combine the best of both worlds with a modular approach that learns a spatial representation of a scene that is trained to be effective when coupled with traditional geometric planners.
-
TANGO: Training-free Embodied AI Agents for Open-world Tasks5 Dec 2024 0 repositories listedLarge Language Models (LLMs) have demonstrated excellent capabilities in composing various modules together to create programs that can perform complex reasoning tasks on images.
-
MPVO: Motion-Prior based Visual Odometry for PointGoal Navigation7 Nov 2024 0 repositories listedVisual odometry (VO) is essential for enabling accurate point-goal navigation of embodied agents in indoor environments where GPS and compass sensors are unreliable and inaccurate.
-
MOPA: Modular Object Navigation with PointGoal Agents7 Apr 2023 0 repositories listedWe propose a simple but effective modular approach MOPA (Modular ObjectNav with PointGoal agents) to systematically investigate the inherent modularity of the object navigation task in Embodied AI.
-
Emergence of Maps in the Memories of Blind Navigation Agents30 Jan 2023 0 repositories listedAnimal navigation research posits that organisms build and maintain internal spatial representations, or maps, of their environment.
-
Unsupervised Visual Odometry and Action Integration for PointGoal Navigation in Indoor Environment2 Oct 2022 0 repositories listedPointGoal navigation in indoor environment is a fundamental task for personal robots to navigate to a specified point.
-
Benchmarking Augmentation Methods for Learning Robust Navigation Agents: the Winning Entry of the 2021 iGibson Challenge22 Sep 2021 0 repositories listedRecent advances in deep reinforcement learning and scalable photorealistic simulation have led to increasingly mature embodied AI for various visual tasks, including navigation.
-
The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation26 Aug 2021 0 repositories listedIt is fundamental for personal robots to reliably navigate to a specified goal.
-
GridToPix: Training Embodied Agents with Minimal Supervision14 Apr 2021 0 repositories listedWhile deep reinforcement learning (RL) promises freedom from hand-labeled data, great successes, especially for Embodied AI, require significant work to create supervision via carefully shaped rewards.
-
THDA: Treasure Hunt Data Augmentation for Semantic Navigation1 Jan 2021 0 repositories listedCan general-purpose neural models learn to navigate?
-
How to Train PointGoal Navigation Agents on a (Sample and Compute) Budget11 Dec 2020 0 repositories listedPointGoal navigation has seen significant recent interest and progress, spurred on by the Habitat platform and associated challenge.
Syntology lines on 6 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections