Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.00936 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915825764532224 |
|---|---|
| author | Zhao, Jinyang Zheng, Handong Zhong, Yanjiu Zhang, Qiang Kang, Yu Wu, Shunyu |
| author_facet | Zhao, Jinyang Zheng, Handong Zhong, Yanjiu Zhang, Qiang Kang, Yu Wu, Shunyu |
| contents | Trajectory generation for mobile robots in unstructured environments faces a critical dilemma: balancing kinematic smoothness for safe execution with terminal precision for fine-grained tasks. Existing generative planners often struggle with this trade-off, yielding either smooth but imprecise paths or geometrically accurate but erratic motions. To address the aforementioned shortcomings, this article proposes DRIFT (Diffusion-based Rule-Inferred for Trajectories), a conditional diffusion framework designed to generate high-fidelity reference trajectories by integrating two complementary inductive biases. First, a Relational Inductive Bias, realized via a GNN-based Structured Scene Perception (SSP) module, encodes global topological constraints to ensure holistic smoothness. Second, a Temporal Attention Bias, implemented through a novel Graph-Conditioned Time-Aware GRU (GTGRU), dynamically attends to sparse obstacles and targets for precise local maneuvering. In the end, quantitative results demonstrate that DRIFT reconciles these conflicting objectives, achieving centimeter-level imitation fidelity (0.041m FDE) and competitive smoothness (27.19 Jerk). This balance yields highly executable reference plans for downstream control. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_00936 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DRIFT: Diffusion-based Rule-Inferred For Trajectories Zhao, Jinyang Zheng, Handong Zhong, Yanjiu Zhang, Qiang Kang, Yu Wu, Shunyu Robotics Trajectory generation for mobile robots in unstructured environments faces a critical dilemma: balancing kinematic smoothness for safe execution with terminal precision for fine-grained tasks. Existing generative planners often struggle with this trade-off, yielding either smooth but imprecise paths or geometrically accurate but erratic motions. To address the aforementioned shortcomings, this article proposes DRIFT (Diffusion-based Rule-Inferred for Trajectories), a conditional diffusion framework designed to generate high-fidelity reference trajectories by integrating two complementary inductive biases. First, a Relational Inductive Bias, realized via a GNN-based Structured Scene Perception (SSP) module, encodes global topological constraints to ensure holistic smoothness. Second, a Temporal Attention Bias, implemented through a novel Graph-Conditioned Time-Aware GRU (GTGRU), dynamically attends to sparse obstacles and targets for precise local maneuvering. In the end, quantitative results demonstrate that DRIFT reconciles these conflicting objectives, achieving centimeter-level imitation fidelity (0.041m FDE) and competitive smoothness (27.19 Jerk). This balance yields highly executable reference plans for downstream control. |
| title | DRIFT: Diffusion-based Rule-Inferred For Trajectories |
| topic | Robotics |
| url | https://arxiv.org/abs/2603.00936 |