DocuMint: Docstring Generation for Python using Small Language Models

Effective communication, specifically through documentation, is the beating heart of collaboration among contributors in software development. Recent advancements in language models (LMs) have enabled the introduction of a new type of actor in that ecosystem: LM-powered assistants capable of code generation, optimization, and maintenance. Our study investigates the efficacy of small language models (SLMs) for generating high-quality docstrings by assessing accuracy, conciseness, and clarity, benchmarking performance quantitatively through mathematical formulas and qualitatively through human evaluation using Likert scale. Further, we introduce DocuMint, as a large-scale supervised fine-tuning dataset with 100,000 samples. In quantitative experiments, Llama 3 8B achieved the best performance across all metrics, with conciseness and clarity scores of 0.605 and 64.88, respectively. However, under human evaluation, CodeGemma 7B achieved the highest overall score with an average of 8.3 out of 10 across all metrics. Fine-tuning the CodeGemma 2B model using the DocuMint dataset led to significant improvements in performance across all metrics, with gains of up to 22.5% in conciseness. The fine-tuned model and the dataset can be found in HuggingFace and the code can be found in the repository.

CARL: Congestion-Aware Reinforcement Learning for Imitation-based Perturbations in Mixed Traffic Control

Human-driven vehicles (HVs) exhibit complex and diverse behaviors. Accurately modeling such behavior is crucial for validating Robot Vehicles (RVs) in simulation and realizing the potential of mixed traffic control. However, existing approaches like parameterized models and data-driven techniques struggle to capture the full complexity and diversity. To address this, in this work, we introduce CARL, a hybrid technique combining imitation learning for close proximity car-following and probabilistic sampling for larger headways. We also propose two classes of RL-based RVs: a safety RV focused on maximizing safety and an efficiency RV focused on maximizing efficiency. Our experiments show that the safety RV increases Time-to-Collision above the critical 4 second threshold and reduces Deceleration Rate to Avoid a Crash by up to 80%, while the efficiency RV achieves improvements in throughput of up to 49%. These results demonstrate the effectiveness of CARL in enhancing both safety and efficiency in mixed traffic.

Beyond Simulated Drivers: Evaluating the Impact of Real-World Car-Following in Mixed Traffic Control

Human-driven vehicles can amplify naturally occurring perturbations in traffic, leading to congestion and consequently increased fuel consumption, higher collision risks, and reduced capacity utilization. While previous research has highlighted that a fraction of Robot Vehicles (RVs) can mitigate these issues, they often rely on simulations with simplistic, model-based Human-driven Vehicles (HVs) during car-following scenarios. Diverging from this trend, in this study, we analyze real-world human driving trajectories, extracting a wide range of acceleration behaviors during car-following. We then incorporate these behaviors in simulation where RVs from prior studies are employed to mitigate congestion, and evaluate their safety, efficiency, and stability. Further, we also introduce a reinforcement learning based RV that utilizes a congestion stage classifier neural network to optimize either "safety+stability" or "efficiency" in the presence of the diverse human driving behaviors. We evaluate the proposed RVs in two different mixed traffic control environments at various densities, configurations, and penetration rates and compare with the existing RVs.

Can ChatGPT Enable ITS? The Case of Mixed Traffic Control via Reinforcement Learning

The surge in Reinforcement Learning (RL) applications in Intelligent Transportation Systems (ITS) has contributed to its growth as well as highlighted key challenges. However, defining objectives of RL agents in traffic control and management tasks, as well as aligning policies with these goals through an effective formulation of Markov Decision Process (MDP), can be challenging and often require domain experts in both RL and ITS. Recent advancements in Large Language Models (LLMs) such as GPT-4 highlight their broad general knowledge, reasoning capabilities, and commonsense priors across various domains. In this work, we conduct a large-scale user study involving 70 participants to investigate whether novices can leverage ChatGPT to solve complex mixed traffic control problems. Three environments are tested, including ring road, bottleneck, and intersection. We find ChatGPT has mixed results. For intersection and bottleneck, ChatGPT increases number of successful policies by 150% and 136% compared to solely beginner capabilities, with some of them even outperforming experts. However, ChatGPT does not provide consistent improvements across all scenarios.

Efficient Quality-Diversity Optimization through Diverse Quality Species

A prevalent limitation of optimizing over a single objective is that it can be misguided, becoming trapped in local optimum. This can be rectified by Quality-Diversity (QD) algorithms, where a population of high-quality and diverse solutions to a problem is preferred. Most conventional QD approaches, for example, MAP-Elites, explicitly manage a behavioral archive where solutions are broken down into predefined niches. In this work, we show that a diverse population of solutions can be found without the limitation of needing an archive or defining the range of behaviors in advance. Instead, we break down solutions into independently evolving species and use unsupervised skill discovery to learn diverse, high-performing solutions. We show that this can be done through gradient-based mutations that take on an information theoretic perspective of jointly maximizing mutual information and performance. We propose Diverse Quality Species (DQS) as an alternative to archive-based QD algorithms. We evaluate it over several simulated robotic environments and show that it can learn a diverse set of solutions from varying species. Furthermore, our results show that DQS is more sample-efficient and performant when compared to other QD algorithms. Relevant code and hyper-parameters are available at: https://github.com/rwickman/NEAT_RL.

Hybrid Traffic Control and Coordination from Pixels

Traffic congestion is a persistent problem in our society. Existing methods for traffic control have proven futile in alleviating current congestion levels leading researchers to explore ideas with robot vehicles given the increased emergence of vehicles with different levels of autonomy on our roads. This gives rise to hybrid traffic control, where robot vehicles regulate human-driven vehicles, through reinforcement learning (RL). However, most existing studies use precise observations that involve global information, such as network throughput, as well as local information, such as vehicle positions and velocities. Obtaining this information requires updating existing road infrastructure with vast sensor networks and communication to potentially unwilling human drivers. We consider image observations as the alternative for hybrid traffic control via RL: 1) images are readily available through satellite imagery, in-car camera systems, and traffic monitoring systems; 2) Images do not require a complete re-imagination of the observation space from network to network; and 3) images only require communication to equipment. In this work, we show that robot vehicles using image observations can achieve similar performance to using precise information on networks, including ring, figure eight, merge, bottleneck, and intersections. We also demonstrate increased performance (up to 26%) in certain cases on tested networks, despite only using local traffic information as opposed to global traffic information.

AutoJoin: Efficient Adversarial Training for Robust Maneuvering via Denoising Autoencoder and Joint Learning

As a result of increasingly adopted machine learning algorithms and ubiquitous sensors, many 'perception-to-control' systems have been deployed in various settings. For these systems to be trustworthy, we need to improve their robustness with adversarial training being one approach. In this work, we propose a gradient-free adversarial training technique, called AutoJoin. AutoJoin is a very simple yet effective and efficient approach to produce robust models for imaged-based autonomous maneuvering. Compared to other SOTA methods with testing on over 5M perturbed and clean images, AutoJoin achieves significant performance increases up to the 40% range under perturbed datasets while improving on clean performance for almost every dataset tested. In particular, AutoJoin can triple the clean performance improvement compared to the SOTA work by Shen et al. Regarding efficiency, AutoJoin demonstrates strong advantages over other SOTA techniques by saving up to 83% time per training epoch and 90% training data. The core idea of AutoJoin is to use a decoder attachment to the original regression model creating a denoising autoencoder within the architecture. This allows the tasks 'steering' and 'denoising sensor input' to be jointly learnt and enable the two tasks to reinforce each other's performance.

Black-box Adversarial Attacks on Network-wide Multi-step Traffic State Prediction Models

Traffic state prediction is necessary for many Intelligent Transportation Systems applications. Recent developments of the topic have focused on network-wide, multi-step prediction, where state of the art performance is achieved via deep learning models, in particular, graph neural network-based models. While the prediction accuracy of deep learning models is high, these models' robustness has raised many safety concerns, given that imperceptible perturbations added to input can substantially degrade the model performance. In this work, we propose an adversarial attack framework by treating the prediction model as a black-box, i.e., assuming no knowledge of the model architecture, training data, and (hyper)parameters. However, we assume that the adversary can oracle the prediction model with any input and obtain corresponding output. Next, the adversary can train a substitute model using input-output pairs and generate adversarial signals based on the substitute model. To test the attack effectiveness, two state of the art, graph neural network-based models (GCGRNN and DCRNN) are examined. As a result, the adversary can degrade the target model's prediction accuracy up to $54\%$. In comparison, two conventional statistical models (linear regression and historical average) are also examined. While these two models do not produce high prediction accuracy, they are either influenced negligibly (less than $3\%$) or are immune to the adversary's attack.

Learning to Control Direct Current Motor for Steering in Real Time via Reinforcement Learning

Model free techniques have been successful at optimal control of complex systems at an expense of copious amounts of data and computation. However, it is often desired to obtain a control policy in a short period of time with minimal data use and computational burden. To this end, we make use of the NFQ algorithm for steering position control of a golf cart in both a real hardware and a simulated environment that was built from real-world interaction. The controller learns to apply a sequence of voltage signals in the presence of environmental uncertainties and inherent non-linearities that challenge the the control task. We were able to increase the rate of successful control under four minutes in simulation and under 11 minutes in real hardware.