Intention-Based Lane Changing and Lane Keeping Haptic Guidance Steering System
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This paper addresses the limitations of current haptic guidance steering (HGS) systems in semi-automated vehicles, specifically their inability to effectively assist with lane changing (LC) maneuvers. While HGS systems excel at lane keeping (LK), switching between LK and LC assistance is challenging due to their opposing control objectives. The authors propose an Intention-Based Haptic Steering (IBHS) system that automatically detects driver intent to change lanes and adjusts assistance accordingly, aiming to improve safety and driving performance. The IBHS system architecture integrates a deep learning-based prediction model, trajectory planning, and an intention consistency module. The prediction model utilizes a Gated Recurrent Unit (GRU) network trained on driving simulator data, including head movement, acceleration, velocity, and steering angles, to predict lane crossing intentions with 94.8% accuracy. Upon detecting an intent, the system plans a trajectory using a 5th-order Bézier curve. A novel intention consistency detection method, based on modified pseudo-work calculations, determines if the driver and system are aligned. If inconsistent, the system adaptively reduces haptic torque gain to transfer control authority back to the driver and replans the trajectory. To evaluate the system, a driving simulator experiment was conducted with 12 participants. The study employed a 2x3 factorial design testing two factors: haptic torque strength (Strong vs. Weak) and LC trajectory speed (Rapid, Normal, Gentle). Participants completed seven trials: one manual driving trial and six assisted trials varying these parameters. The scenario involved a straight expressway with induced lane changes. Performance metrics included lane departure risk, lateral error, and subjective assessments of workload and comfort. The results demonstrated that the IBHS system significantly reduced lane departure risks during lane keeping tasks compared to manual driving. For lane changing, the system supported fast and stable maneuvers. The adaptive gain control effectively managed conflicts between driver and system intentions, preventing steering shaking and allowing smooth transitions. The study concluded that intention-based haptic guidance is a viable method for shared control, offering improved safety and reduced workload. The findings provide a foundation for designing DAS systems that seamlessly switch between lane keeping and lane changing assistance, enhancing the overall user experience in semi-automated driving.
Key finding
The intention-based haptic guidance steering system decreased lane departure risk in lane keeping tasks and supported faster, stable lane changing maneuvers compared to manual driving.
Methodology
simulator
Sample size: 12
Provenance
The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed. Discovered via verifier_tag_review on 2026-05-08 (3 acquisition events logged).
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | — | — | — | 1 | 2026-05-07 |
| archive | success | canonical_url | — | — | 7 | 2026-06-06 |
| extract | success | cached | — | — | 3 | 2026-06-10 |
| clean | success | clean | — | — | 1 | 2026-06-04 |
| chunk | success | chunk | — | — | 1 | 2026-06-04 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-04 |
| enrich | success | — | — | — | 1 | 2026-05-07 |
| promote | success | — | — | — | 1 | 2026-05-07 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 2 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 15 | 2026-06-11 |
| verify | success | — | — | — | 2 | 2026-06-10 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.