Search

Reinforcement learning (RL) methods for social robot navigation show great success navigating robots through large crowds of people, but the performance of these learning-based methods tends to degrade in particularly challenging or unfamiliar situations due to the models' dependency on representative training data. To ensure human safety and comfort, it is critical that these algorithms handle uncommon cases appropriately, but the low frequency and wide diversity of such situations present a significant challenge for these data-driven methods. To overcome this challenge, we propose modifications to the learning process that encourage these RL policies to maintain additional caution in unfamiliar situations. Specifically, we improve the Socially Attentive Reinforcement Learning (SARL) policy by (1) modifying the training process to systematically introduce deviations into a pedestrian model, (2) updating the value network to estimate and utilize pedestrian-unpredictability features, and (3) implementing a reward function to learn an effective response to pedestrian unpredictability. Compared to the original SARL policy, our modified policy maintains similar navigation times and path lengths, while reducing the number of collisions by 82% and reducing the proportion of time spent in the pedestrians' personal space by up to 19 percentage points for the most difficult cases. We also describe how to apply these modifications to other RL policies and demonstrate that some key high-level behaviors of our approach transfer to a physical robot.

Human children far exceed modern machine learning algorithms in their sample efficiency, achieving high performance in key domains with much less data than current models. This ''data gap'' is a key challenge both for building intelligent artificial systems and for understanding human development. Egocentric video capturing children's experience -- their ''training data'' -- is a key ingredient for comparison of humans and models and for the development of algorithmic innovations to bridge this gap. Yet there are few such datasets available, and extant data are low-resolution, have limited metadata, and importantly, represent only a small set of children's experiences. Here, we provide the first release of the largest developmental egocentric video dataset to date -- the BabyView dataset -- recorded using a high-resolution camera with a large vertical field-of-view and gyroscope/accelerometer data. This 493 hour dataset includes egocentric videos from children spanning 6 months - 5 years of age in both longitudinal, at-home contexts and in a preschool environment. We provide gold-standard annotations for the evaluation of speech transcription, speaker diarization, and human pose estimation, and evaluate models in each of these domains. We train self-supervised language and vision models and evaluate their transfer to out-of-distribution tasks including syntactic structure learning, object recognition, depth estimation, and image segmentation. Although performance in each scales with dataset size, overall performance is relatively lower than when models are trained on curated datasets, especially in the visual domain. Our dataset stands as an open challenge for robust, humanlike AI systems: how can such systems achieve human-levels of success on the same scale and distribution of training data as humans?, Comment: 9 pages, 2 figures, 4 tables and SI. Submitted to NeurIPS Datasets and Benchmarks

How (dis)similar are the learning trajectories of vision-language models and children? Recent modeling work has attempted to understand the gap between models' and humans' data efficiency by constructing models trained on less data, especially multimodal naturalistic data. However, such models are often evaluated on adult-level benchmarks, with limited breadth in language abilities tested, and without direct comparison to behavioral data. We introduce DevBench, a multimodal benchmark comprising seven language evaluation tasks spanning the domains of lexical, syntactic, and semantic ability, with behavioral data from both children and adults. We evaluate a set of vision-language models on these tasks, comparing models and humans not only on accuracy but on their response patterns. Across tasks, models exhibit variation in their closeness to human response patterns, and models that perform better on a task also more closely resemble human behavioral responses. We also examine the developmental trajectory of OpenCLIP over training, finding that greater training results in closer approximations to adult response patterns. DevBench thus provides a benchmark for comparing models to human language development. These comparisons highlight ways in which model and human language learning processes diverge, providing insight into entry points for improving language models.

Large language models (LLMs) have achieved state-of-the-art results in many natural language processing tasks. They have also demonstrated ability to adapt well to different tasks through zero-shot or few-shot settings. With the capability of these LLMs, researchers have looked into how to adopt them for use with Visual Question Answering (VQA). Many methods require further training to align the image and text embeddings. However, these methods are computationally expensive and requires large scale image-text dataset for training. In this paper, we explore a method of combining pretrained LLMs and other foundation models without further training to solve the VQA problem. The general idea is to use natural language to represent the images such that the LLM can understand the images. We explore different decoding strategies for generating textual representation of the image and evaluate their performance on the VQAv2 dataset.

Contrastive learning has shown to learn better quality representations than models trained using cross-entropy loss. They also transfer better to downstream datasets from different domains. However, little work has been done to explore the transferability of representations learned using contrastive learning when trained on a multi-domain dataset. In this paper, a study has been conducted using the Supervised Contrastive Learning framework to learn representations from the multi-domain DomainNet dataset and then evaluate the transferability of the representations learned on other downstream datasets. The fixed feature linear evaluation protocol will be used to evaluate the transferability on 7 downstream datasets that were chosen across different domains. The results obtained are compared to a baseline model that was trained using the widely used cross-entropy loss. Empirical results from the experiments showed that on average, the Supervised Contrastive Learning model performed 6.05% better than the baseline model on the 7 downstream datasets. The findings suggest that Supervised Contrastive Learning models can potentially learn more robust representations that transfer better across domains than cross-entropy models when trained on a multi-domain dataset.

Software remodularization through clustering is a common practice to improve internal software quality. However, the true benefit of software clustering is only realized if developers follow through with the recommended refactoring suggestions, which can be complex and time-consuming. Simply producing clustering results is not enough to realize the benefits of remodularization. For the recommended refactoring operations to have an impact, developers must follow through with them. However, this is often a difficult task due to certain refactoring operations' complexity and time-consuming nature., Comment: Accepted for publication at ICSE23 Poster Track

The deployment of machine learning models in safety-critical applications comes with the expectation that such models will perform well over a range of contexts (e.g., a vision model for classifying street signs should work in rural, city, and highway settings under varying lighting/weather conditions). However, these one-size-fits-all models are typically optimized for average case performance, encouraging them to achieve high performance in nominal conditions but exposing them to unexpected behavior in challenging or rare contexts. To address this concern, we develop a new method for training context-dependent models. We extend Bridge-Mode Connectivity (BMC) (Garipov et al., 2018) to train an infinite ensemble of models over a continuous measure of context such that we can sample model parameters specifically tuned to the corresponding evaluation context. We explore the definition of context in image classification tasks through multiple lenses including changes in the risk profile, long-tail image statistics/appearance, and context-dependent distribution shift. We develop novel extensions of the BMC optimization for each of these cases and our experiments demonstrate that model performance can be successfully tuned to context in each scenario., Comment: Accepted to the NeurIPS 2022 ML Safety Workshop

Reconfigurable metamaterials require constituent nanostructures to demonstrate switching of shapes with external stimuli. For generality, such nanostructures would touch and stick to other surfaces in one of its configurations. Yet, a longstanding challenge is in overcoming this stiction caused by Van der Waals forces, which impedes shape recovery. Here, we introduce a stiff yet self-recovering material system based on acrylic acid, and tested it in high-aspect ratio structures, where recovery is weak. This designer material has a storage modulus of ~5.2 GPa at room temperature and ~90 MPa in the rubbery state at 150 Celsius, an order of magnitude higher than previous reports. A high-resolution resin for two-photon lithography was developed based on this polymer system, enabling 3D printing of nanopillars with diameters of ~400 nm and aspect ratio as high as ~10. Experimentally, we observed self-recovery as collapsed and touching structures overcome stiction to stand back up. We developed a theoretical model to explain the recoverability of these sub-micron structures. Reconfigurable structural colour prints and holograms were demonstrated, indicating potential applications of the material system as a shape memory polymer suitable for sub-micron reconfigurable metamaterials.

Maintenance of existing software requires a large amount of time for comprehending the source code. The architecture of a software, however, may not be clear to maintainers if up to date documentations are not available. Software clustering is often used as a remodularisation and architecture recovery technique to help recover a semantic representation of the software design. Due to the diverse domains, structure, and behaviour of software systems, the suitability of different clustering algorithms for different software systems are not investigated thoroughly. Research that introduce new clustering techniques usually validate their approaches on a specific domain, which might limit its generalisability. If the chosen test subjects could only represent a narrow perspective of the whole picture, researchers might risk not being able to address the external validity of their findings. This work aims to fill this gap by introducing a new approach, Explaining Software Clustering for Remodularisation, to evaluate the effectiveness of different software clustering approaches. This work focuses on hierarchical clustering and Bunch clustering algorithms and provides information about their suitability according to the features of the software, which as a consequence, enables the selection of the most optimum algorithm and configuration from our existing pool of choices for a particular software system. The proposed framework is tested on 30 open source software systems with varying sizes and domains, and demonstrates that it can characterise both the strengths and weaknesses of the analysed software clustering algorithms using software features extracted from the code. The proposed approach also provides a better understanding of the algorithms behaviour through the application of dimensionality reduction techniques., Comment: 31 pages

We investigate the initiation of cracks in vertically freestanding water-saturated colloidal pillars constructed using a direct-write technique. Paradoxically, the cracks form during drying at the free end, far from the substrate, where the particle network is unconstrained in contracting its volume as it bears compression by a uniform capillary pressure acting at its outer surface. This is explained by a dominant balance of wetting energy terms, from which follows a simple relationship between the particle size and pillar dimensions that captures the presence or absence of cracks. This relationship provides a practical guideline for fabricating crack-free colloidal structures., Comment: 11 pages, 2 figures