Offline imitation learning (IL) refers to learning expert behavior solely from demonstrations, without any additional interaction with the environment. Despite significant advances in offline IL, existing techniques find it challenging to learn policies for long-horizon tasks and require significant re-training when task specifications change. Towards addressing these limitations, we present GO-DICE an offline IL technique for goal-conditioned long-horizon sequential tasks. GO-DICE discerns a hierarchy of sub-tasks from demonstrations and uses these to learn separate policies for sub-task transitions and action execution, respectively; this hierarchical policy learning facilitates long-horizon reasoning. Inspired by the expansive DICE-family of techniques, policy learning at both the levels transpires within the space of stationary distributions. Further, both policies are learnt with goal conditioning to minimize need for retraining when task goals change. Experimental results substantiate that GO-DICE outperforms recent baselines, as evidenced by a marked improvement in the completion rate of increasingly challenging pick-and-place Mujoco robotic tasks. GO-DICE is also capable of leveraging imperfect demonstration and partial task segmentation when available, both of which boost task performance relative to learning from expert demonstrations alone.
Due to the modern relevance of blockchain technology, smart contracts present both substantial risks and benefits. Vulnerabilities within them can trigger a cascade of consequences, resulting in significant losses. Many current papers primarily focus on classifying smart contracts for malicious intent, often relying on limited contract characteristics, such as bytecode or opcode. This paper proposes a novel, two-layered framework: 1) classifying and 2) directly repairing malicious contracts. Slither's vulnerability report is combined with source code and passed through a pre-trained RandomForestClassifier (RFC) and Large Language Models (LLMs), classifying and repairing each suggested vulnerability. Experiments demonstrate the effectiveness of fine-tuned and prompt-engineered LLMs. The smart contract repair models, built from pre-trained GPT-3.5-Turbo and fine-tuned Llama-2-7B models, reduced the overall vulnerability count by 97.5% and 96.7% respectively. A manual inspection of repaired contracts shows that all retain functionality, indicating that the proposed method is appropriate for automatic batch classification and repair of vulnerabilities in smart contracts.
Large Language Models (LLMs) pre-trained on code have recently emerged as the dominant approach to program synthesis. However, the code that these models produce can violate basic language-level invariants, leading to lower performance in downstream tasks. We address this issue through an approach, called RLCF, that further trains a pre-trained LLM using feedback from a code compiler. RLCF views the LLM as an RL agent that generates code step by step and receives: (i) compiler-derived feedback on whether the code it generates passes a set of correctness checks; and (ii) feedback from a different LLM on whether the generated code is similar to a set of reference programs in the training corpus. Together, these feedback mechanisms help the generated code remain within the target distribution while passing all static correctness checks. RLCF is model- and language-agnostic. We empirically evaluate it on the MBJP and MathQA tasks for Java. Our experiments show that RLCF significantly raises the odds that an LLM-generated program compiles, is executable, and produces the right output on tests, often allowing LLMs to match the performance of 2x-8x larger LLMs.
Many applications such as forensics, surveillance, satellite imaging, medical imaging, etc., demand High-Resolution (HR) images. However, obtaining an HR image is not always possible due to the limitations of optical sensors and their costs. An alternative solution called Single Image Super-Resolution (SISR) is a software-driven approach that aims to take a Low-Resolution (LR) image and obtain the HR image. Most supervised SISR solutions use ground truth HR image as a target and do not include the information provided in the LR image, which could be valuable. In this work, we introduce Triplet Loss-based Generative Adversarial Network hereafter referred as SRTGAN for Image Super-Resolution problem on real-world degradation. We introduce a new triplet-based adversarial loss function that exploits the information provided in the LR image by using it as a negative sample. Allowing the patch-based discriminator with access to both HR and LR images optimizes to better differentiate between HR and LR images; hence, improving the adversary. Further, we propose to fuse the adversarial loss, content loss, perceptual loss, and quality loss to obtain Super-Resolution (SR) image with high perceptual fidelity. We validate the superior performance of the proposed method over the other existing methods on the RealSR dataset in terms of quantitative and qualitative metrics.
The quality of training data has a huge impact on the efficiency, accuracy and complexity of machine learning tasks. Various tools and techniques are available that assess data quality with respect to general cleaning and profiling checks. However these techniques are not applicable to detect data issues in the context of machine learning tasks, like noisy labels, existence of overlapping classes etc. We attempt to re-look at the data quality issues in the context of building a machine learning pipeline and build a tool that can detect, explain and remediate issues in the data, and systematically and automatically capture all the changes applied to the data. We introduce the Data Quality Toolkit for machine learning as a library of some key quality metrics and relevant remediation techniques to analyze and enhance the readiness of structured training datasets for machine learning projects. The toolkit can reduce the turn-around times of data preparation pipelines and streamline the data quality assessment process. Our toolkit is publicly available via IBM API Hub [1] platform, any developer can assess the data quality using the IBM's Data Quality for AI apis [2]. Detailed tutorials are also available on IBM Learning Path [3].
Accurate reconstruction of static environments from LiDAR scans of scenes containing dynamic objects, which we refer to as Dynamic to Static Translation (DST), is an important area of research in Autonomous Navigation. This problem has been recently explored for visual SLAM, but to the best of our knowledge no work has been attempted to address DST for LiDAR scans. The problem is of critical importance due to wide-spread adoption of LiDAR in Autonomous Vehicles. We show that state-of the art methods developed for the visual domain when adapted for LiDAR scans perform poorly. We develop DSLR, a deep generative model which learns a mapping between dynamic scan to its static counterpart through an adversarially trained autoencoder. Our model yields the first solution for DST on LiDAR that generates static scans without using explicit segmentation labels. DSLR cannot always be applied to real world data due to lack of paired dynamic-static scans. Using Unsupervised Domain Adaptation, we propose DSLR-UDA for transfer to real world data and experimentally show that this performs well in real world settings. Additionally, if segmentation information is available, we extend DSLR to DSLR-Seg to further improve the reconstruction quality. DSLR gives the state of the art performance on simulated and real-world datasets and also shows at least 4x improvement. We show that DSLR, unlike the existing baselines, is a practically viable model with its reconstruction quality within the tolerable limits for tasks pertaining to autonomous navigation like SLAM in dynamic environments.
We address the problem of adapting robot trajectories to improve safety, comfort, and efficiency in human-robot collaborative tasks. To this end, we propose CoMOTO, a trajectory optimization framework that utilizes stochastic motion prediction models to anticipate the human's motion and adapt the robot's joint trajectory accordingly. We design a multi-objective cost function that simultaneously optimizes for i) separation distance, ii) visibility of the end-effector, iii) legibility, iv) efficiency, and v) smoothness. We evaluate CoMOTO against three existing methods for robot trajectory generation when in close proximity to humans. Our experimental results indicate that our approach consistently outperforms existing methods over a combined set of safety, comfort, and efficiency metrics.
Robot task execution when situated in real-world environments is fragile. As such, robot architectures must rely on robust error recovery, adding non-trivial complexity to highly-complex robot systems. To handle this complexity in development, we introduce Recovery-Driven Development (RDD), an iterative task scripting process that facilitates rapid task and recovery development by leveraging hierarchical specification, separation of nominal task and recovery development, and situated testing. We validate our approach with our challenge-winning mobile manipulator software architecture developed using RDD for the FetchIt! Challenge at the IEEE 2019 International Conference on Robotics and Automation. We attribute the success of our system to the level of robustness achieved using RDD, and conclude with lessons learned for developing such systems.
In this paper, we explore the task of robot sculpting. We propose a search based planning algorithm to solve the problem of sculpting by material removal with a multi-axis manipulator. We generate collision free trajectories for a manipulator using best-first search in voxel space. We also show significant speedup of our algorithm by using octrees to decompose the voxel space. We demonstrate our algorithm on a multi-axis manipulator in simulation by sculpting Michelangelo's Statue of David, evaluate certain metrics of our algorithm and discuss future goals for the project.