pith. sign in

arxiv: 1803.00653 · v1 · pith:O6A4NWSQnew · submitted 2018-03-01 · 💻 cs.LG · cs.AI· cs.CV· cs.RO

Semi-parametric Topological Memory for Navigation

classification 💻 cs.LG cs.AIcs.CVcs.RO
keywords navigationagentgraphmemorynodessptmtopologicalcorresponding
0
0 comments X
read the original abstract

We introduce a new memory architecture for navigation in previously unseen environments, inspired by landmark-based navigation in animals. The proposed semi-parametric topological memory (SPTM) consists of a (non-parametric) graph with nodes corresponding to locations in the environment and a (parametric) deep network capable of retrieving nodes from the graph based on observations. The graph stores no metric information, only connectivity of locations corresponding to the nodes. We use SPTM as a planning module in a navigation system. Given only 5 minutes of footage of a previously unseen maze, an SPTM-based navigation agent can build a topological map of the environment and use it to confidently navigate towards goals. The average success rate of the SPTM agent in goal-directed navigation across test environments is higher than the best-performing baseline by a factor of three. A video of the agent is available at https://youtu.be/vRF7f4lhswo

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Recover, Discover, Plan: Learning Skills and Concepts from Robot Failures

    cs.RO 2026-06 unverdicted novelty 7.0

    ReSYNC learns recovery skills via RL then discovers and refines relational predicates to enable abstract planning that generalizes failure avoidance to unseen long-horizon tasks, outperforming baselines by over 50% in...

  2. Topology-Aware State Abstraction with Tangle Cores for Markov Decision Processes

    cs.LG 2026-05 unverdicted novelty 7.0

    Tangle-core abstraction creates overlapping state abstractions for MDPs from graph tangles, with value-preservation guarantees under action consistency and improved empirical compression-return tradeoffs in bottleneck...

  3. AnyImageNav: Any-View Geometry for Precise Last-Meter Image-Goal Navigation

    cs.RO 2026-04 unverdicted novelty 7.0

    AnyImageNav uses a semantic-to-geometric cascade with 3D multi-view foundation models to recover precise 6-DoF poses from goal images, achieving 0.27m position error and state-of-the-art success rates on Gibson and HM...

  4. Mitigating Error Accumulation in Continuous Navigation via Memory-Augmented Kalman Filtering

    cs.RO 2026-01 unverdicted novelty 7.0

    NeuroKalman mitigates state drift in vision-language UAV navigation by using memory-augmented Kalman filtering where attention retrieves historical anchors to correct predictions without gradient updates.

  5. Do As I Can, Not As I Say: Grounding Language in Robotic Affordances

    cs.RO 2022-04 accept novelty 7.0

    SayCan combines an LLM's high-level semantic knowledge with robot skill value functions to select only feasible actions, enabling completion of abstract natural-language instructions on a real mobile manipulator.

  6. QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL

    cs.LG 2026-05 unverdicted novelty 6.0

    QHyer achieves state-of-the-art results in offline goal-conditioned RL by replacing return-to-go with a state-conditioned Q-estimator and introducing a gated hybrid attention-mamba backbone for content-adaptive histor...

  7. QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL

    cs.LG 2026-05 unverdicted novelty 6.0

    QHyer replaces return-to-go with a state-conditioned Q-estimator and adds a gated hybrid attention-mamba backbone to achieve state-of-the-art performance in offline goal-conditioned RL on both Markovian and non-Markov...

  8. Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning

    cs.LG 2026-04 conditional novelty 6.0

    Occupancy Reward Shaping extracts goal-reaching rewards from world-model occupancy measures using optimal transport, improving offline goal-conditioned RL performance 2.2x on 13 tasks without changing the optimal policy.

  9. FeudalNav: A Simple Framework for Visual Navigation

    cs.RO 2026-01 unverdicted novelty 6.0

    FeudalNav decomposes visual navigation into hierarchical levels with a visual-similarity latent memory, delivering competitive Habitat AI results without any odometry.

  10. MASt3R-Nav: WayPixel Navigation in Relative 3D Maps

    cs.RO 2026-05 unverdicted novelty 5.0

    MASt3R-Nav proposes pixel-relative connectivity graphs from image sequences to create WayPixel Costmaps that condition a controller for improved visual navigation without global geometric consistency.

  11. A Hamilton-Jacobi Reachability-Guided Search Framework for Efficient and Safe Indoor Planar Robot Navigation

    cs.RO 2026-04 unverdicted novelty 5.0

    A hybrid navigation system uses offline HJ reachability computations as heuristics and safety constraints within graph search to achieve faster and safer robot movement in complex indoor environments.