Deployment in hazardous environments requires robots to understand the risks associated with their actions and movements to prevent accidents. Despite its importance, these risks are not explicitly modeled by currently deployed locomotion controllers for legged robots. In this work, we propose a risk sensitive locomotion training method employing distributional reinforcement learning to consider safety explicitly. Instead of relying on a value expectation, we estimate the complete value distribution to account for uncertainty in the robot's interaction with the environment. The value distribution is consumed by a risk metric to extract risk sensitive value estimates. These are integrated into Proximal Policy Optimization (PPO) to derive our method, Distributional Proximal Policy Optimization (DPPO). The risk preference, ranging from risk-averse to risk-seeking, can be controlled by a single parameter, which enables to adjust the robot's behavior dynamically. Importantly, our approach removes the need for additional reward function tuning to achieve risk sensitivity. We show emergent risk sensitive locomotion behavior in simulation and on the quadrupedal robot ANYmal.

Research in explainable AI (XAI) aims to provide insights into the decision-making process of opaque AI models. To date, most XAI methods offer one-off and static explanations, which cannot cater to the diverse backgrounds and understanding levels of users. With this paper, we investigate if free-form conversations can enhance users' comprehension of static explanations, improve acceptance and trust in the explanation methods, and facilitate human-AI collaboration. Participants are presented with static explanations, followed by a conversation with a human expert regarding the explanations. We measure the effect of the conversation on participants' ability to choose, from three machine learning models, the most accurate one based on explanations and their self-reported comprehension, acceptance, and trust. Empirical results show that conversations significantly improve comprehension, acceptance, trust, and collaboration. Our findings highlight the importance of customized model explanations in the format of free-form conversations and provide insights for the future design of conversational explanations.

Segmentation of the sigmoid colon is a crucial aspect of treating diverticulitis. It enables accurate identification and localisation of inflammation, which in turn helps healthcare professionals make informed decisions about the most appropriate treatment options. This research presents a novel deep learning architecture for segmenting the sigmoid colon from Computed Tomography (CT) images using a modified 3D U-Net architecture. Several variations of the 3D U-Net model with modified hyper-parameters were examined in this study. Pyramid pooling (PyP) and channel-spatial Squeeze and Excitation (csSE) were also used to improve the model performance. The networks were trained using manually annotated sigmoid colon. A five-fold cross-validation procedure was used on a test dataset to evaluate the network's performance. As indicated by the maximum Dice similarity coefficient (DSC) of 56.92+/-1.42%, the application of PyP and csSE techniques improves segmentation precision. We explored ensemble methods including averaging, weighted averaging, majority voting, and max ensemble. The results show that average and majority voting approaches with a threshold value of 0.5 and consistent weight distribution among the top three models produced comparable and optimal results with DSC of 88.11+/-3.52%. The results indicate that the application of a modified 3D U-Net architecture is effective for segmenting the sigmoid colon in Computed Tomography (CT) images. In addition, the study highlights the potential benefits of integrating ensemble methods to improve segmentation precision.

Federated learning has emerged as a viable distributed solution to train machine learning models without the actual need to share data with the central aggregator. However, standard neural network-based federated learning models have been shown to be susceptible to data leakage from the gradients shared with the server. In this work, we introduce federated learning with variational quantum circuit model built using expressive encoding maps coupled with overparameterized ans\"atze. We show that expressive maps lead to inherent privacy against gradient inversion attacks, while overparameterization ensures model trainability. Our privacy framework centers on the complexity of solving the system of high-degree multivariate Chebyshev polynomials generated by the gradients of quantum circuit. We present compelling arguments highlighting the inherent difficulty in solving these equations, both in exact and approximate scenarios. Additionally, we delve into machine learning-based attack strategies and establish a direct connection between overparameterization in the original federated learning model and underparameterization in the attack model. Furthermore, we provide numerical scaling arguments showcasing that underparameterization of the expressive map in the attack model leads to the loss landscape being swamped with exponentially many spurious local minima points, thus making it extremely hard to realize a successful attack. This provides a strong claim, for the first time, that the nature of quantum machine learning models inherently helps prevent data leakage in federated learning.

We propose FLARE, the first fingerprinting mechanism to verify whether a suspected Deep Reinforcement Learning (DRL) policy is an illegitimate copy of another (victim) policy. We first show that it is possible to find non-transferable, universal adversarial masks, i.e., perturbations, to generate adversarial examples that can successfully transfer from a victim policy to its modified versions but not to independently trained policies. FLARE employs these masks as fingerprints to verify the true ownership of stolen DRL policies by measuring an action agreement value over states perturbed by such masks. Our empirical evaluations show that FLARE is effective (100% action agreement on stolen copies) and does not falsely accuse independent policies (no false positives). FLARE is also robust to model modification attacks and cannot be easily evaded by more informed adversaries without negatively impacting agent performance. We also show that not all universal adversarial masks are suitable candidates for fingerprints due to the inherent characteristics of DRL policies. The spatio-temporal dynamics of DRL problems and sequential decision-making process make characterizing the decision boundary of DRL policies more difficult, as well as searching for universal masks that capture the geometry of it.

We investigate how robotic camera systems can offer new capabilities to computer-supported cooperative work through the design, development, and evaluation of a prototype system called Periscope. With Periscope, a local worker completes manipulation tasks with guidance from a remote helper who observes the workspace through a camera mounted on a semi-autonomous robotic arm that is co-located with the worker. Our key insight is that the helper, the worker, and the robot should all share responsibility of the camera view--an approach we call shared camera control. Using this approach, we present a set of modes that distribute the control of the camera between the human collaborators and the autonomous robot depending on task needs. We demonstrate the system's utility and the promise of shared camera control through a preliminary study where 12 dyads collaboratively worked on assembly tasks. Finally, we discuss design and research implications of our work for future robotic camera systems that facilitate remote collaboration.

Current captioning datasets focus on object-centric captions, describing the visible objects in the image, e.g. "people eating food in a park". Although these datasets are useful to evaluate the ability of Vision & Language models to recognize and describe visual content, they do not support controlled experiments involving model testing or fine-tuning, with more high-level captions, which humans find easy and natural to produce. For example, people often describe images based on the type of scene they depict ('people at a holiday resort') and the actions they perform ('people having a picnic'). Such descriptions draw on personal experience and commonsense assumptions. We present the High-Level Dataset a dataset extending 14997 images from the COCO dataset, aligned with a new set of 134,973 human-annotated (high-level) captions collected along three axes: scenes, actions, and rationales. We further extend this dataset with confidence scores collected from an independent set of readers, as well as a set of narrative captions generated synthetically, by combining each of the three axes. We describe this dataset and analyse it extensively. We also present baseline results for the High-Level Captioning task.

What could be more delightful than a trip to Greece to meet Yanis Varoufakis, the charismatic leftwing firebrand who tried to stick it to the man, AKA the IMF, EU and entire global financial order? The mental imagery I have before the visit is roughly two parts Zorba the Greek to one part an episode of BBC series Holiday from the Jill Dando era: blue skies, blue sea, maybe some plate breaking in a jolly taverna. What I'm not expecting is a wall of flames rippling across a hillside next to the highway from the airport and a plume of black smoke billowing across the carriageway. Because even a modernist villa on a hillside on the island of Aegina – a fast ferry ride from the port of Piraeus and the summer bolthole of chic Athenians – is not the sanctuary from the modern world that it might once have been. The house is where Varoufakis and his wife, landscape artist Danae Stratou, live, year round since the pandemic, but in August 2023 at the end of a summer of heatwaves and extreme weather conditions across the world, it feels more than a little apocalyptic. The sun is a dim orange orb struggling to shine through a haze of smoke while a shower of fine ash falls invisibly from the sky.

Generic sentence embeddings provide a coarse-grained approximation of semantic textual similarity but ignore specific aspects that make texts similar. Conversely, aspect-based sentence embeddings provide similarities between texts based on certain predefined aspects. Thus, similarity predictions of texts are more targeted to specific requirements and more easily explainable. In this paper, we present AspectCSE, an approach for aspect-based contrastive learning of sentence embeddings. Results indicate that AspectCSE achieves an average improvement of 3.97% on information retrieval tasks across multiple aspects compared to the previous best results. We also propose using Wikidata knowledge graph properties to train models of multi-aspect sentence embeddings in which multiple specific aspects are simultaneously considered during similarity predictions. We demonstrate that multi-aspect embeddings outperform single-aspect embeddings on aspect-specific information retrieval tasks. Finally, we examine the aspect-based sentence embedding space and demonstrate that embeddings of semantically similar aspect labels are often close, even without explicit similarity training between different aspect labels.

Disentangling uncorrelated information in speech utterances is a crucial research topic within speech community. Different speech-related tasks focus on extracting distinct speech representations while minimizing the affects of other uncorrelated information. We present a large-scale speech corpus to facilitate the research of speech representation disentanglement. 3D-Speaker contains over 10,000 speakers, each of whom are simultaneously recorded by multiple Devices, locating at different Distances, and some speakers are speaking multiple Dialects. The controlled combinations of multi-dimensional audio data yield a matrix of a diverse blend of speech representation entanglement, thereby motivating intriguing methods to untangle them. The multi-domain nature of 3D-Speaker also makes it a suitable resource to evaluate large universal speech models and experiment methods of out-of-domain learning and self-supervised learning. https://3dspeaker.github.io/