LLM as Runtime Error Handler: A Promising Pathway to Adaptive Self-Healing of Software Systems

Unanticipated runtime errors, lacking predefined handlers, can abruptly terminate execution and lead to severe consequences, such as data loss or system crashes. Despite extensive efforts to identify potential errors during the development phase, such unanticipated errors remain a challenge to to be entirely eliminated, making the runtime mitigation measurements still indispensable to minimize their impact. Automated self-healing techniques, such as reusing existing handlers, have been investigated to reduce the loss coming through with the execution termination. However, the usability of existing methods is retained by their predefined heuristic rules and they fail to handle diverse runtime errors adaptively. Recently, the advent of Large Language Models (LLMs) has opened new avenues for addressing this problem. Inspired by their remarkable capabilities in understanding and generating code, we propose to deal with the runtime errors in a real-time manner using LLMs. Specifically, we propose Healer, the first LLM-assisted self-healing framework for handling runtime errors. When an unhandled runtime error occurs, Healer will be activated to generate a piece of error-handling code with the help of its internal LLM and the code will be executed inside the runtime environment owned by the framework to obtain a rectified program state from which the program should continue its execution. Our exploratory study evaluates the performance of Healer using four different code benchmarks and three state-of-the-art LLMs, GPT-3.5, GPT-4, and CodeQwen-7B. Results show that, without the need for any fine-tuning, GPT-4 can successfully help programs recover from 72.8% of runtime errors, highlighting the potential of LLMs in handling runtime errors.

High-Quality, ROS Compatible Video Encoding and Decoding for High-Definition Datasets

Robotic datasets are important for scientific benchmarking and developing algorithms, for example for Simultaneous Localization and Mapping (SLAM). Modern robotic datasets feature video data of high resolution and high framerates. Storing and sharing those datasets becomes thus very costly, especially if more than one camera is used for the datasets. It is thus essential to store this video data in a compressed format. This paper investigates the use of modern video encoders for robotic datasets. We provide a software that can replay mp4 videos within ROS 1 and ROS 2 frameworks, supporting the synchronized playback in simulated time. Furthermore, the paper evaluates different encoders and their settings to find optimal configurations in terms of resulting size, quality and encoding time. Through this work we show that it is possible to store and share even highest quality video datasets within reasonable storage constraints.

Collecting Larg-Scale Robotic Datasets on a High-Speed Mobile Platform

Mobile robotics datasets are essential for research on robotics, for example for research on Simultaneous Localization and Mapping (SLAM). Therefore the ShanghaiTech Mapping Robot was constructed, that features a multitude high-performance sensors and a 16-node cluster to collect all this data. That robot is based on a Clearpath Husky mobile base with a maximum speed of 1 meter per second. This is fine for indoor datasets, but to collect large-scale outdoor datasets a faster platform is needed. This system paper introduces our high-speed mobile platform for data collection. The mapping robot is secured on the rear-steered flatbed car with maximum field of view. Additionally two encoders collect odometry data from two of the car wheels and an external sensor plate houses a downlooking RGB and event camera. With this setup a dataset of more than 10km in the underground parking garage and the outside of our campus was collected and is published with this paper.

Benchmarking SLAM Algorithms in the Cloud: The SLAM Hive System

Evaluating the performance of Simultaneous Localization and Mapping (SLAM) algorithms is essential for scientists and users of robotic systems alike. But there are a multitude different permutations of possible options of hardware setups and algorithm configurations, as well as different datasets and algorithms, such that it is infeasible to thoroughly compare SLAM systems against the full state of the art. To solve that we present the SLAM Hive Benchmarking Suite, which is able to analyze SLAM algorithms in thousands of mapping runs, through its utilization of container technology and deployment in the cloud. This paper presents the architecture and open source implementation of SLAM Hive and compares it to existing efforts on SLAM evaluation. We perform mapping runs of many of the most popular visual and LiDAR based SLAM algorithms against commonly used datasets and show how SLAM Hive and then be used to conveniently analyze the results against various aspects. Through this we envision that SLAM Hive can become an essential tool for proper comparisons and evaluations of SLAM algorithms and thus drive the scientific development in the research on SLAM. The open source software as well as a demo to show the live analysis of 100s of mapping runs can be found on our SLAM Hive website.

ShanghaiTech Mapping Robot is All You Need: Robot System for Collecting Universal Ground Vehicle Datasets

This paper presents the ShanghaiTech Mapping Robot, a state-of-the-art unmanned ground vehicle (UGV) designed for collecting comprehensive multi-sensor datasets to support research in robotics, computer vision, and autonomous driving. The robot is equipped with a wide array of sensors including RGB cameras, RGB-D cameras, event-based cameras, IR cameras, LiDARs, mmWave radars, IMUs, ultrasonic range finders, and a GNSS RTK receiver. The sensor suite is integrated onto a specially designed mechanical structure with a centralized power system and a synchronization mechanism to ensure spatial and temporal alignment of the sensor data. A 16-node on-board computing cluster handles sensor control, data collection, and storage. We describe the hardware and software architecture of the robot in detail and discuss the calibration procedures for the various sensors. The capabilities of the platform are demonstrated through an extensive dataset collected in diverse real-world environments. To facilitate research, we make the dataset publicly available along with the associated robot sensor calibration data. Performance evaluations on a set of standard perception and localization tasks showcase the potential of the dataset to support developments in Robot Autonomy.

Trojans in Large Language Models of Code: A Critical Review through a Trigger-Based Taxonomy

Large language models (LLMs) have provided a lot of exciting new capabilities in software development. However, the opaque nature of these models makes them difficult to reason about and inspect. Their opacity gives rise to potential security risks, as adversaries can train and deploy compromised models to disrupt the software development process in the victims' organization. This work presents an overview of the current state-of-the-art trojan attacks on large language models of code, with a focus on triggers -- the main design point of trojans -- with the aid of a novel unifying trigger taxonomy framework. We also aim to provide a uniform definition of the fundamental concepts in the area of trojans in Code LLMs. Finally, we draw implications of findings on how code models learn on trigger design.

Mixture-of-Instructions: Comprehensive Alignment of a Large Language Model through the Mixture of Diverse System Prompting Instructions

With the proliferation of large language models (LLMs), the comprehensive alignment of such models across multiple tasks has emerged as a critical area of research. Existing alignment methodologies primarily address single task, such as multi-turn dialogue, coding, mathematical problem-solving, and tool usage. However, AI-driven products that leverage language models usually necessitate a fusion of these abilities to function effectively in real-world scenarios. Moreover, the considerable computational resources required for proper alignment of LLMs underscore the need for a more robust, efficient, and encompassing approach to multi-task alignment, ensuring improved generative performance. In response to these challenges, we introduce a novel technique termed Mixture-of-Instructions (MoI), which employs a strategy of instruction concatenation combined with diverse system prompts to boost the alignment efficiency of language models. We have also compiled a diverse set of seven benchmark datasets to rigorously evaluate the alignment efficacy of the MoI-enhanced language model. Our methodology was applied to the open-source Qwen-7B-chat model, culminating in the development of Qwen-SFT-MoI. This enhanced model demonstrates significant advancements in generative capabilities across coding, mathematics, and tool use tasks.

What is Meant by AGI? On the Definition of Artificial General Intelligence

This paper aims to establish a consensus on AGI's definition. General intelligence refers to the adaptation to open environments according to certain principles using limited resources. It emphasizes that adaptation or learning is an indispensable property of intelligence, and places the controversial part within the principles of intelligence, which can be described from different perspectives.

Patched Line Segment Learning for Vector Road Mapping

This paper presents a novel approach to computing vector road maps from satellite remotely sensed images, building upon a well-defined Patched Line Segment (PaLiS) representation for road graphs that holds geometric significance. Unlike prevailing methods that derive road vector representations from satellite images using binary masks or keypoints, our method employs line segments. These segments not only convey road locations but also capture their orientations, making them a robust choice for representation. More precisely, given an input image, we divide it into non-overlapping patches and predict a suitable line segment within each patch. This strategy enables us to capture spatial and structural cues from these patch-based line segments, simplifying the process of constructing the road network graph without the necessity of additional neural networks for connectivity. In our experiments, we demonstrate how an effective representation of a road graph significantly enhances the performance of vector road mapping on established benchmarks, without requiring extensive modifications to the neural network architecture. Furthermore, our method achieves state-of-the-art performance with just 6 GPU hours of training, leading to a substantial 32-fold reduction in training costs in terms of GPU hours.

A Model of Sequential Learning based on Non-Axiomatic Logic

Sequential learning is a fundamental function of an intelligent agent. This technical report introduces a model of sequential learning, which is interpretable through Non-Axiomatic Logic. The learning procedure includes three steps, hypothesizing, revising, and recycling, and can work under the Assumption of Insufficient Knowledge and Resources. Although there are limitations for the current design, the model has been proven effective in some simple cases.