FlexPath: Learned Semantic Path Priors for Image-Based Planning

• URL: http://arxiv.org/abs/2606.10167v1
• Date: Mon, 08 Jun 2026 20:53:11 GMT
• Title: FlexPath: Learned Semantic Path Priors for Image-Based Planning
• Abstract summary: We introduce FlexPath, a two-stage framework that decouples feasibility from preference.<n>For shortest-path planning, FlexPath reduces search effort on TMP by 14.3% compared to the state-of-the-art TransPath.<n>For obstacle clearance with minimum clearance distance 2, it achieves 96.8% full obstacle avoidance while maintaining low search cost.
• Score: 2.739231894601598
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent learning-based path planners use neural networks to process visual map representations and approximate heuristics for classical search algorithms, yielding near-optimal paths with reduced search effort. However, these methods are tied to the shortest-path objective implicit in their supervision, which limits their flexibility to accommodate alternative criteria. We introduce FlexPath, a two-stage framework that decouples feasibility from preference. In Stage 1, we use imitation learning to acquire a task-independent spatial prior over feasible paths from visual map inputs. In Stage 2, differentiable Path Shape Objectives (PSOs) adapt this prior toward task-specific criteria without relearning path structure, requiring only efficient objective-level adaptation. A single pretrained model can be adapted to multiple objectives. For shortest-path planning, FlexPath reduces search effort on TMP by 14.3% compared to the state-of-the-art TransPath, while also finding lower-cost paths on average and demonstrating strong zero-shot generalization across three unseen domains. For obstacle clearance with minimum clearance distance 2, it achieves 96.8% full obstacle avoidance while maintaining low search cost. The framework further extends to semantic-aware avoidance and waypoint guidance via objective-level adaptation, and remains compatible with classical planners at inference time. Data and code are available at https://github.com/FraunhoferIVI/FlexPath.

Related papers

• VikPath: A Vision Kansformer Framework for Effective Obstacle Avoidance in Self-Supervised Pathfinding [12.76109113310209]
  We propose a self-supervised pathfinding framework that considers obstacle proximity and path smoothness.<n>$Design$ achieves an average of 3.28% greater obstacle clearance and 87.07% lower latency while maintaining smooth path generation.
  arXiv  Detail & Related papers  (2026-08-24T00:23:57Z)
• AutoPath: Learning Transferable Goal-Conditioned Stochastic Path Prior for Safe Navigation Without Human Demonstrations [103.61864552260316]
  Real-time navigation in dynamic environments requires collision-free and dynamically feasible motion under limited perception.<n>We formulate navigation as learning a transferable goal-aligned path prior that models a reusable distribution over goal-aligned geometry-consistent local paths conditioned on local observations.<n>We develop a structured prior learning framework that parameterizes local paths using a geometry-aware polar action manifold and incorporates risk-sensitive utility shaping with multi-goal distributional rollouts for stable and safety-aware planning.
  arXiv  Detail & Related papers  (2026-07-13T16:00:41Z)
• Optimal any-angle path planning in static and dynamic environments [3.8673630752805437]
  Zeta* and Zeta*-SIPP are developed for static and dynamic environments respectively.<n>Zeta*-SIPP, with either scanning method, is more than 20 times faster than the corresponding state-of-the-art optimal planner TO-AA-SIPP.
  arXiv  Detail & Related papers  (2026-06-30T12:40:23Z)
• STAR: Semantic-Tuned and Tail-Adaptive Retriever for Graph-Augmented Generation [69.66045538889777]
  We propose STAR, a semantic-tuned and tail-adaptive retriever for GraphRAG.<n> STAR consistently outperforms baselines, achieving average retrieval performance gains of 1.8%.
  arXiv  Detail & Related papers  (2026-04-11T10:16:51Z)
• REST: Receding Horizon Explorative Steiner Tree for Zero-Shot Object-Goal Navigation [31.04470860657085]
  Zero-shot object-goal navigation (ZSON) requires navigating unknown environments to find a target object without task-specific training.<n>We instantiate this insight in textitREST (Receding Horizon Explorative Steiner Tree), a training-free framework that builds an explicit open-vocabulary 3D map from online RGB-D streams.
  arXiv  Detail & Related papers  (2026-03-19T08:43:40Z)
• Transform-Invariant Generative Ray Path Sampling for Efficient Radio Propagation Modeling [5.567300300236187]
  Ray tracing has become a standard for accurate radio propagation modeling, but suffers from computational complexity.<n>We propose a comprehensive machine-learning-assisted framework that replaces exhaustive path searching with intelligent sampling via Generative Flow Networks.
  arXiv  Detail & Related papers  (2026-03-02T09:37:34Z)
• Efficient Path Generation with Curvature Guarantees by Mollification [2.6381163133447836]
  We present a method to regularize non-differentiable functions and generate feasible paths through mollification.<n>Specifically, we approximate an arbitrary path with a differentiable function that can converge to it with arbitrary precision.<n>The proposed approach is analytically more efficient than standard methods, enabling real-time implementation on microcontrollers.
  arXiv  Detail & Related papers  (2025-12-15T10:48:42Z)
• Path-LLM: A Shortest-Path-based LLM Learning for Unified Graph Representation [6.401420962078335]
  We propose a novel Path-LLM model to efficiently learn unified graph representation.<n>Our framework consists of four well-designed techniques.<n>Compared with WalkLM, our approach saves more than 90% of training paths on millions-scale graphs and runs at most 35x faster.
  arXiv  Detail & Related papers  (2024-08-10T06:35:11Z)
• Affordances-Oriented Planning using Foundation Models for Continuous Vision-Language Navigation [64.84996994779443]
  We propose a novel Affordances-Oriented Planner for continuous vision-language navigation (VLN) task. Our AO-Planner integrates various foundation models to achieve affordances-oriented low-level motion planning and high-level decision-making. Experiments on the challenging R2R-CE and RxR-CE datasets show that AO-Planner achieves state-of-the-art zero-shot performance.
  arXiv  Detail & Related papers  (2024-07-08T12:52:46Z)
• LLM-A*: Large Language Model Enhanced Incremental Heuristic Search on Path Planning [91.95362946266577]
  Path planning is a fundamental scientific problem in robotics and autonomous navigation.<n>Traditional algorithms like A* and its variants are capable of ensuring path validity but suffer from significant computational and memory inefficiencies as the state space grows.<n>We propose a new LLM based route planning method that synergistically combines the precise pathfinding capabilities of A* with the global reasoning capability of LLMs.<n>This hybrid approach aims to enhance pathfinding efficiency in terms of time and space complexity while maintaining the integrity of path validity, especially in large-scale scenarios.
  arXiv  Detail & Related papers  (2024-06-20T01:24:30Z)
• GraphWalks: Efficient Shape Agnostic Geodesic Shortest Path Estimation [93.60478281489243]
  We propose a learnable network to approximate geodesic paths on 3D surfaces. The proposed method provides efficient approximations of the shortest paths and geodesic distances estimations.
  arXiv  Detail & Related papers  (2022-05-30T16:22:53Z)
• Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search [60.965024145243596]
  One-shot weight sharing methods have recently drawn great attention in neural architecture search due to high efficiency and competitive performance. To alleviate this problem, we present a simple yet effective architecture distillation method. We introduce the concept of prioritized path, which refers to the architecture candidates exhibiting superior performance during training. Since the prioritized paths are changed on the fly depending on their performance and complexity, the final obtained paths are the cream of the crop.
  arXiv  Detail & Related papers  (2020-10-29T17:55:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.