cs.RONov 2, 2026

TRAILS: Trajectory Generation for Automated Indoor Locomotion Studies

Authors: Juho Kalliokoski, Evan G. Center, Steven M. LaValle, Timo Ojala, Basak Sakcak

Organizations: Faculty of Information Technology and Electrical Engineering, University of Oulu, P.O. Box 4500, Oulu, FI-90014, Finland · Department of Advanced Computing Sciences, Maastricht University, Netherlands

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Virtual reality experiments involving navigation and simulated robot motion often require large, realistic environments and numerous distinct trajectories to avoid repetitive navigation while providing sufficient variation for controlled experiments. Designing such scenarios manually is labor-intensive, particularly when trajectories must satisfy predefined geometric and kinematic constraints while remaining diverse and comparable across experimental conditions. This paper presents TRAILS, an automated framework for generating complete virtual navigation scenarios consisting of an environment layout, a path, and a time-parameterized motion profile. The framework combines a constraint-based procedural environment generator inspired by Wave Function Collapse, trajectory generation using optimized cubic Bézier curves, and speed-profile generation subject to kinematic constraints. The generated scenarios provide diverse indoor environments with corridors, open spaces, and obstacles, together with trajectories of identical duration that vary in path geometry, wall proximity, and velocity profiles while minimizing systematic dependencies between these characteristics. The framework is designed as an easy-to-use tool requiring only a small number of intuitive user-defined parameters to automatically generate large sets of distinct navigation scenarios satisfying prescribed geometric and kinematic constraints. By relying on explicit, seed-controlled algorithmic procedures rather than data-driven models, the generated scenarios remain transparent, reproducible, and configurable, making the framework well suited for telepresence and human-subject experiments. The code is available at https://github.com/JucciK/Trails .

Figures & tables

Fig. 1: Overview of the TRAILS framework.
Fig. 2: Tile adjacency constraints. (Left) Each side of a tile is assigned an interface label. A tile can be placed adjacent to another tile only if the labels on the shared edge are compatible. (Middle) Compatible neighboring tiles satisfying adjacency constraints. (Right) Incompatible neighboring tiles.
Fig. 3: Example environment (top-view) generated by the proposed framework together with four generated paths.
Fig. 4: Linear velocity profiles corresponding to the trajectories shown in Fig. 3 . The profiles consist of piecewise constant-velocity segments connected by constant-acceleration transitions while satisfying the prescribed motion constraints.
ParameterValue
Minimum number of tiles500
Maximum endpoint offset αmax⁡\alpha_{\max}0.4
Maximum control-point angle ϕmax⁡\phi_{\max}1.0 rad
Control-point distance [dmin⁡,dmax⁡][d_{\min},d_{\max}][0.25,1.5][0.25,1.5] m
Minimum wall clearance dwalld_{\mathrm{wall}}0.30 m
Maximum angular velocity ωmax⁡\omega_{\max}π\pi rad/s
TABLE I: Parameters used in the numerical example.
More in this topic

Procedural Material Generation

See all 8 papers

Explore similar work

CardsList
Apr 5, 2026

InsTraj: Instructing Diffusion Models with Travel Intentions to Generate Real-world Trajectories

The generation of realistic and controllable GPS trajectories is a fundamental task for applications in urban planning, mobility simulation, and privacy-preserving data sharing. However, existing methods face a two-fold challenge: they lack the deep semantic understanding to interpret complex user travel intent, and struggle to handle complex constraints while maintaining the realistic diversity inherent in human behavior. To resolve this, we introduce InsTraj, a novel framework that instructs diffusion models to generate high-fidelity trajectories directly from natural language descriptions. Specifically, InsTraj first utilizes a powerful large language model to decipher unstructured travel intentions formed in natural language, thereby creating rich semantic blueprints and bridging the representation gap between intentions and trajectories. Subsequently, we proposed a multimodal trajectory diffusion transformer that can integrate semantic guidance to generate high-fidelity and instruction-faithful trajectories that adhere to fine-grained user intent. Comprehensive experiments on real-world datasets demonstrate that InsTraj significantly outperforms state-of-the-art methods in generating trajectories that are realistic, diverse, and semantically faithful to the input instructions.

Yuanshao Zhu, Yuxuan Liang, Xiangyu Zhao +5

Southern University of Science and Technology · City University of Hong Kong · The Hong Kong University of Science and Technology (Guangzhou) +2

Trajectory GenerationDiffusion Models for Motion Generation
AskPDF
Jun 10, 2026

TrajGenAgent: A Hierarchical LLM Agent for Human Mobility Trajectory Generation

Human mobility data is important for transportation, urban planning, and epidemic control, but large-scale trajectory collection is often costly and privacy-constrained, motivating realistic synthetic trajectory generation. Existing LLM-based generators typically rely on either prompt engineering, which preserves zero-shot reasoning but lacks fine-grained spatiotemporal grounding, or trajectory-level fine-tuning, which improves statistical precision but incurs substantial computational cost and may weaken general reasoning. We propose TrajGenAgent, a semantic-aware hierarchical LLM-agent framework for human mobility trajectory generation without model fine-tuning. TrajGenAgent uses a two-stage orchestrator-worker design: an LLM first synthesizes an individual- and weekday-conditioned activity chain from historical evidence via in-context learning, and a deterministic workflow then grounds each activity into a complete visit using personalized POI retrieval, distance-aware location selection, kinematics-aware travel-time propagation, and LLM-based duration estimation. To evaluate realism beyond aggregate spatiotemporal statistics, we introduce an anomaly-detection-based evaluation framework using two complementary detectors to assess behavioral and semantic plausibility. Experiments on benchmark and large-scale simulation datasets show that TrajGenAgent improves spatiotemporal fidelity, semantic coherence, and individual-specific behavioral realism over representative neural and LLM-based baselines, while avoiding parameter updates.

Siyu Li, Toan Tran, Lingyi Zhao +2

Dept. of Computer Science, Emory University, Atlanta, GA, USA · Novateur Research Solutions, Ashburn, VA, USA

Trajectory GenerationHuman Behavior SimulationSynthetic Data GenerationLLM Agent Trajectory SynthesisLLM Agent Planning
AskPDF
Mar 19, 2026

V-Dreamer: Automating Robotic Simulation and Trajectory Synthesis via Video Generation Priors

Training generalist robots demands large-scale, diverse manipulation data, yet real-world collection is prohibitively expensive, and existing simulators are often constrained by fixed asset libraries and manual heuristics. To bridge this gap, we present V-Dreamer, a fully automated framework that generates open-vocabulary, simulation-ready manipulation environments and executable expert trajectories directly from natural language instructions. V-Dreamer employs a novel generative pipeline that constructs physically grounded 3D scenes using large language models and 3D generative models, validated by geometric constraints to ensure stable, collision-free layouts. Crucially, for behavior synthesis, we leverage video generation models as rich motion priors. These visual predictions are then mapped into executable robot trajectories via a robust Sim-to-Gen visual-kinematic alignment module utilizing CoTracker3 and VGGT. This pipeline supports high visual diversity and physical fidelity without manual intervention. To evaluate the generated data, we train imitation learning policies on synthesized trajectories encompassing diverse object and environment variations. Extensive evaluations on tabletop manipulation tasks using the Piper robotic arm demonstrate that our policies robustly generalize to unseen objects in simulation and achieve effective sim-to-real transfer, successfully manipulating novel real-world objects.

Songjia He, Zixuan Chen, Hongyu Ding +5

Nanjing University. · Northwestern Polytechnical University.

Synthetic Data Generation for RoboticsRobotic ManipulationTrajectory GenerationRobotics SimulationRobot Motion Generation
AskPDF