Enhancing Autonomous Driving Systems with On-Board Deployed Large Language Models

Neural Networks (NNs) trained through supervised learning struggle with managing edge-case scenarios common in real-world driving due to the intractability of exhaustive datasets covering all edge-cases, making knowledge-driven approaches, akin to how humans intuitively detect unexpected driving behavior, a suitable complement to data-driven methods. This work proposes a hybrid architecture combining low-level Model Predictive Controller (MPC) with locally deployed Large Language Models (LLMs) to enhance decision-making and Human Machine Interaction (HMI). The DecisionxLLM module evaluates robotic state information against natural language instructions to ensure adherence to desired driving behavior. The MPCxLLM module then adjusts MPC parameters based on LLM-generated insights, achieving control adaptability while preserving the safety and constraint guarantees of traditional MPC systems. Further, to enable efficient on-board deployment and to eliminate dependency on cloud connectivity, we shift processing to the on-board computing platform: We propose an approach that exploits Retrieval Augmented Generation (RAG), Low Rank Adaptation (LoRA) fine-tuning, and quantization. Experimental results demonstrate that these enhancements yield significant improvements in reasoning accuracy by up to 10.45%, control adaptability by as much as 52.2%, and up to 10.5x increase in computational efficiency (tokens/s), validating the proposed framework's practicality for real-time deployment even on down-scaled robotic platforms. This work bridges high-level decision-making with low-level control adaptability, offering a synergistic framework for knowledge-driven and adaptive Autonomous Driving Systems (ADS).

Towards Low-Latency Event-based Obstacle Avoidance on a FPGA-Drone

This work quantitatively evaluates the performance of event-based vision systems (EVS) against conventional RGB-based models for action prediction in collision avoidance on an FPGA accelerator. Our experiments demonstrate that the EVS model achieves a significantly higher effective frame rate (1 kHz) and lower temporal (-20 ms) and spatial prediction errors (-20 mm) compared to the RGB-based model, particularly when tested on out-of-distribution data. The EVS model also exhibits superior robustness in selecting optimal evasion maneuvers. In particular, in distinguishing between movement and stationary states, it achieves a 59 percentage point advantage in precision (78% vs. 19%) and a substantially higher F1 score (0.73 vs. 0.06), highlighting the susceptibility of the RGB model to overfitting. Further analysis in different combinations of spatial classes confirms the consistent performance of the EVS model in both test data sets. Finally, we evaluated the system end-to-end and achieved a latency of approximately 2.14 ms, with event aggregation (1 ms) and inference on the processing unit (0.94 ms) accounting for the largest components. These results underscore the advantages of event-based vision for real-time collision avoidance and demonstrate its potential for deployment in resource-constrained environments.

TinyCenterSpeed: Efficient Center-Based Object Detection for Autonomous Racing

Perception within autonomous driving is nearly synonymous with Neural Networks (NNs). Yet, the domain of autonomous racing is often characterized by scaled, computationally limited robots used for cost-effectiveness and safety. For this reason, opponent detection and tracking systems typically resort to traditional computer vision techniques due to computational constraints. This paper introduces TinyCenterSpeed, a streamlined adaptation of the seminal CenterPoint method, optimized for real-time performance on 1:10 scale autonomous racing platforms. This adaptation is viable even on OBCs powered solely by Central Processing Units (CPUs), as it incorporates the use of an external Tensor Processing Unit (TPU). We demonstrate that, compared to Adaptive Breakpoint Detector (ABD), the current State-of-the-Art (SotA) in scaled autonomous racing, TinyCenterSpeed not only improves detection and velocity estimation by up to 61.38% but also supports multi-opponent detection and estimation. It achieves real-time performance with an inference time of just 7.88 ms on the TPU, significantly reducing CPU utilization 8.3-fold.

GP-enhanced Autonomous Drifting Framework using ADMM-based iLQR

Autonomous drifting is a complex challenge due to the highly nonlinear dynamics and the need for precise real-time control, especially in uncertain environments. To address these limitations, this paper presents a hierarchical control framework for autonomous vehicles drifting along general paths, primarily focusing on addressing model inaccuracies and mitigating computational challenges in real-time control. The framework integrates Gaussian Process (GP) regression with an Alternating Direction Method of Multipliers (ADMM)-based iterative Linear Quadratic Regulator (iLQR). GP regression effectively compensates for model residuals, improving accuracy in dynamic conditions. ADMM-based iLQR not only combines the rapid trajectory optimization of iLQR but also utilizes ADMM's strength in decomposing the problem into simpler sub-problems. Simulation results demonstrate the effectiveness of the proposed framework, with significant improvements in both drift trajectory tracking and computational efficiency. Our approach resulted in a 38$\%$ reduction in RMSE lateral error and achieved an average computation time that is 75$\%$ lower than that of the Interior Point OPTimizer (IPOPT).

FSDP: Fast and Safe Data-Driven Overtaking Trajectory Planning for Head-to-Head Autonomous Racing Competitions

Generating overtaking trajectories in autonomous racing is a challenging task, as the trajectory must satisfy the vehicle's dynamics and ensure safety and real-time performance running on resource-constrained hardware. This work proposes the Fast and Safe Data-Driven Planner to address this challenge. Sparse Gaussian predictions are introduced to improve both the computational efficiency and accuracy of opponent predictions. Furthermore, the proposed approach employs a bi-level quadratic programming framework to generate an overtaking trajectory leveraging the opponent predictions. The first level uses polynomial fitting to generate a rough trajectory, from which reference states and control inputs are derived for the second level. The second level formulates a model predictive control optimization problem in the Frenet frame, generating a trajectory that satisfies both kinematic feasibility and safety. Experimental results on the F1TENTH platform show that our method outperforms the State-of-the-Art, achieving an 8.93% higher overtaking success rate, allowing the maximum opponent speed, ensuring a smoother ego trajectory, and reducing 74.04% computational time compared to the Predictive Spliner method. The code is available at: https://github.com/ZJU-DDRX/FSDP.

RLPP: A Residual Method for Zero-Shot Real-World Autonomous Racing on Scaled Platforms

Autonomous racing presents a complex environment requiring robust controllers capable of making rapid decisions under dynamic conditions. While traditional controllers based on tire models are reliable, they often demand extensive tuning or system identification. RL methods offer significant potential due to their ability to learn directly from interaction, yet they typically suffer from the Sim-to-Reall gap, where policies trained in simulation fail to perform effectively in the real world. In this paper, we propose RLPP, a residual RL framework that enhances a PP controller with an RL-based residual. This hybrid approach leverages the reliability and interpretability of PP while using RL to fine-tune the controller's performance in real-world scenarios. Extensive testing on the F1TENTH platform demonstrates that RLPP improves lap times by up to 6.37 %, closing the gap to the SotA methods by more than 52 % and providing reliable performance in zero-shot real-world deployment, overcoming key challenges associated with the Sim-to-Real transfer and reducing the performance gap from simulation to reality by more than 8-fold when compared to the baseline RL controller. The RLPP framework is made available as an open-source tool, encouraging further exploration and advancement in autonomous racing research. The code is available at: www.github.com/forzaeth/rlpp.

ElectraSight: Smart Glasses with Fully Onboard Non-Invasive Eye Tracking Using Hybrid Contact and Contactless EOG

Smart glasses with integrated eye tracking technology are revolutionizing diverse fields, from immersive augmented reality experiences to cutting-edge health monitoring solutions. However, traditional eye tracking systems rely heavily on cameras and significant computational power, leading to high-energy demand and privacy issues. Alternatively, systems based on electrooculography (EOG) provide superior battery life but are less accurate and primarily effective for detecting blinks, while being highly invasive. The paper introduces ElectraSight, a non-invasive plug-and-play low-power eye tracking system for smart glasses. The hardware-software co-design of the system is detailed, along with the integration of a hybrid EOG (hEOG) solution that incorporates both contact and contactless electrodes. Within 79 kB of memory, the proposed tinyML model performs real-time eye movement classification with 81% accuracy for 10 classes and 92% for 6 classes, not requiring any calibration or user-specific fine-tuning. Experimental results demonstrate that ElectraSight delivers high accuracy in eye movement and blink classification, with minimal overall movement detection latency (90% within 60 ms) and an ultra-low computing time (301 {\mu}s). The power consumption settles down to 7.75 mW for continuous data acquisition and 46 mJ for the tinyML inference. This efficiency enables continuous operation for over 3 days on a compact 175 mAh battery. This work opens new possibilities for eye tracking in commercial applications, offering an unobtrusive solution that enables advancements in user interfaces, health diagnostics, and hands-free control systems.

Noise Analysis and Modeling of the PMD Flexx2 Depth Camera for Robotic Applications

Time of Flight ToF cameras renowned for their ability to capture realtime 3D information have become indispensable for agile mobile robotics These cameras utilize light signals to accurately measure distances enabling robots to navigate complex environments with precision Innovative depth cameras characterized by their compact size and lightweight design such as the recently released PMD Flexx2 are particularly suited for mobile robots Capable of achieving high frame rates while capturing depth information this innovative sensor is suitable for tasks such as robot navigation and terrain mapping Operating on the ToF measurement principle the sensor offers multiple benefits over classic stereobased depth cameras However the depth images produced by the camera are subject to noise from multiple sources complicating their simulation This paper proposes an accurate quantification and modeling of the nonsystematic noise of the PMD Flexx2 We propose models for both axial and lateral noise across various camera modes assuming Gaussian distributions Axial noise modeled as a function of distance and incidence angle demonstrated a low average KullbackLeibler KL divergence of 0015 nats reflecting precise noise characterization Lateral noise deviating from a Gaussian distribution was modeled conservatively yielding a satisfactory KL divergence of 0868 nats These results validate our noise models crucial for accurately simulating sensor behavior in virtual environments and reducing the simtoreal gap in learningbased control approaches

Autonomous Navigation in Dynamic Human Environments with an Embedded 2D LiDAR-based Person Tracker

In the rapidly evolving landscape of autonomous mobile robots, the emphasis on seamless human-robot interactions has shifted towards autonomous decision-making. This paper delves into the intricate challenges associated with robotic autonomy, focusing on navigation in dynamic environments shared with humans. It introduces an embedded real-time tracking pipeline, integrated into a navigation planning framework for effective person tracking and avoidance, adapting a state-of-the-art 2D LiDAR-based human detection network and an efficient multi-object tracker. By addressing the key components of detection, tracking, and planning separately, the proposed approach highlights the modularity and transferability of each component to other applications. Our tracking approach is validated on a quadruped robot equipped with 270{\deg} 2D-LiDAR against motion capture system data, with the preferred configuration achieving an average MOTA of 85.45% in three newly recorded datasets, while reliably running in real-time at 20 Hz on the NVIDIA Jetson Xavier NX embedded GPU-accelerated platform. Furthermore, the integrated tracking and avoidance system is evaluated in real-world navigation experiments, demonstrating how accurate person tracking benefits the planner in optimizing the generated trajectories, enhancing its collision avoidance capabilities. This paper contributes to safer human-robot cohabitation, blending recent advances in human detection with responsive planning to navigate shared spaces effectively and securely.

A Proximity-Based Approach for Dynamically Matching Industrial Assets and Their Operators Using Low-Power IoT Devices

Asset tracking solutions have proven their significance in industrial contexts, as evidenced by their successful commercialization (e.g., Hilti On!Track). However, a seamless solution for matching assets with their users, such as operators of construction power tools, is still missing. By enabling assetuser matching, organizations gain valuable insights that can be used to optimize user health and safety, asset utilization, and maintenance. This paper introduces a novel approach to address this gap by leveraging existing Bluetooth Low Energy (BLE)-enabled low-power Internet of Things (IoT) devices. The proposed framework comprises the following components: i) a wearable device, ii) an IoT device attached to or embedded in the assets, iii) an algorithm to estimate the distance between assets and operators by exploiting simple received signal strength indicator (RSSI) measurements via an Extended Kalman Filter (EKF), and iv) a cloud-based algorithm that collects all estimated distances to derive the correct asset-operator matching. The effectiveness of the proposed system has been validated through indoor and outdoor experiments in a construction setting for identifying the operator of a power tool. A physical prototype was developed to evaluate the algorithms in a realistic setup. The results demonstrated a median accuracy of 0.49m in estimating the distance between assets and users, and up to 98.6% in correctly matching users with their assets.