Steady Path: Ensuring Stability in Autonomous Industrial Maneuvering

Autonomous Industrial Vehicles (AIVs) operating in warehouses and industrial facilities must navigate constrained layouts while responding to stationary and moving obstacles.A path that is geometrically collision-free may still produce undesirable motion if vehicle dynamics and terminal behavior are not considered during control.This paper presents SteadyPath, a simulation-based framework for stability-aware autonomous industrial maneuvering.The framework combines a virtual perception layer based on simulator-generated ground-truth object positions and distances, vehicle-state estimation, obstacle-aware decision-making, A* path planning, and Model Predictive Control with terminal constraints.The MPC controller predicts future vehicle motion over a finite horizon and selects steering and longitudinal control actions while seeking a stable terminal condition.The system is evaluated using four scenario tests and a quantitative comparison against a baseline controller.In the reported mission benchmark, the proposed controller completed the mission in 76.4 s compared with 85.6 s for the baseline, reduced mean tracking error from 14.61 m to 2.52 m, reduced peak lateral deviation from 18.91 m to 5.25 m, and increased the clearance buffer margin from 1.30 m to 3.60 m.Both controllers recorded zero dynamic detours or re-plans in the benchmark.The proposed controller was recorded as reaching an invariant stable terminal set, while the baseline was recorded as having a lagging boundary.Scenario testing showed successful outcomes for normal-road, static-obstacle, and fully blocked-road cases; the moving-obstacle case requires clarification because its textual result says the obstacle was handled safely while its status is marked FAIL.The findings indicate improved performance on the reported simulation metrics, while further testing is required to establish robustness across broader dynamic conditions and real sensor inputs.

Authors

Institutions

Publication Details

Journal
IJARCCE
Published
2026-11-18
DOI
https://doi.org/10.17148/ijarcce.2026.1511147
Primary Topic
Robotic Path Planning Algorithms
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Steady Path: Ensuring Stability in Autonomous Industrial Maneuvering

Snehal B, Rudra Prathap Singh, Diwakar M, Shashank D N et al.
3 links
IJARCCE
Robotic Path Planning Algorithms
article

Steady Path: Ensuring Stability in Autonomous Industrial Maneuvering

Snehal B, Rudra Prathap Singh, Diwakar M, Shashank D N, B. C. Hemapriya
article en

Abstract

Autonomous Industrial Vehicles (AIVs) operating in warehouses and industrial facilities must navigate constrained layouts while responding to stationary and moving obstacles.A path that is geometrically collision-free may still produce undesirable motion if vehicle dynamics and terminal behavior are not considered during control.This paper presents SteadyPath, a simulation-based framework for stability-aware autonomous industrial maneuvering.The framework combines a virtual perception layer based on simulator-generated ground-truth object positions and distances, vehicle-state estimation, obstacle-aware decision-making, A* path planning, and Model Predictive Control with terminal constraints.The MPC controller predicts future vehicle motion over a finite horizon and selects steering and longitudinal control actions while seeking a stable terminal condition.The system is evaluated using four scenario tests and a quantitative comparison against a baseline controller.In the reported mission benchmark, the proposed controller completed the mission in 76.4 s compared with 85.6 s for the baseline, reduced mean tracking error from 14.61 m to 2.52 m, reduced peak lateral deviation from 18.91 m to 5.25 m, and increased the clearance buffer margin from 1.30 m to 3.60 m.Both controllers recorded zero dynamic detours or re-plans in the benchmark.The proposed controller was recorded as reaching an invariant stable terminal set, while the baseline was recorded as having a lagging boundary.Scenario testing showed successful outcomes for normal-road, static-obstacle, and fully blocked-road cases; the moving-obstacle case requires clarification because its textual result says the obstacle was handled safely while its status is marked FAIL.The findings indicate improved performance on the reported simulation metrics, while further testing is required to establish robustness across broader dynamic conditions and real sensor inputs.

IJARCCEVol. 15(11)
East West Institute of Technology (IN)
Industry, innovation and infrastructure
Robotic Path Planning Algorithms
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon