EnvoDat: A Large-Scale Multisensory Dataset for Robotic Spatial Awareness and Semantic Reasoning in Heterogeneous Environments

To ensure the efficiency of robot autonomy under diverse real-world conditions, a high-quality heterogeneous dataset is essential to benchmark the operating algorithms' performance and robustness. Current benchmarks predominantly focus on urban terrains, specifically for on-road autonomous driving, leaving multi-degraded, densely vegetated, dynamic and feature-sparse environments, such as underground tunnels, natural fields, and modern indoor spaces underrepresented. To fill this gap, we introduce EnvoDat, a large-scale, multi-modal dataset collected in diverse environments and conditions, including high illumination, fog, rain, and zero visibility at different times of the day. Overall, EnvoDat contains 26 sequences from 13 scenes, 10 sensing modalities, over 1.9TB of data, and over 89K fine-grained polygon-based annotations for more than 82 object and terrain classes. We post-processed EnvoDat in different formats that support benchmarking SLAM and supervised learning algorithms, and fine-tuning multimodal vision models. With EnvoDat, we contribute to environment-resilient robotic autonomy in areas where the conditions are extremely challenging. The datasets and other relevant resources can be accessed through https://linusnep.github.io/EnvoDat/.

ED-VAE: Entropy Decomposition of ELBO in Variational Autoencoders

Traditional Variational Autoencoders (VAEs) are constrained by the limitations of the Evidence Lower Bound (ELBO) formulation, particularly when utilizing simplistic, non-analytic, or unknown prior distributions. These limitations inhibit the VAE's ability to generate high-quality samples and provide clear, interpretable latent representations. This work introduces the Entropy Decomposed Variational Autoencoder (ED-VAE), a novel re-formulation of the ELBO that explicitly includes entropy and cross-entropy components. This reformulation significantly enhances model flexibility, allowing for the integration of complex and non-standard priors. By providing more detailed control over the encoding and regularization of latent spaces, ED-VAE not only improves interpretability but also effectively captures the complex interactions between latent variables and observed data, thus leading to better generative performance.

Multimodal Human-Autonomous Agents Interaction Using Pre-Trained Language and Visual Foundation Models

In this paper, we extended the method proposed in [17] to enable humans to interact naturally with autonomous agents through vocal and textual conversations. Our extended method exploits the inherent capabilities of pre-trained large language models (LLMs), multimodal visual language models (VLMs), and speech recognition (SR) models to decode the high-level natural language conversations and semantic understanding of the robot's task environment, and abstract them to the robot's actionable commands or queries. We performed a quantitative evaluation of our framework's natural vocal conversation understanding with participants from different racial backgrounds and English language accents. The participants interacted with the robot using both spoken and textual instructional commands. Based on the logged interaction data, our framework achieved 87.55% vocal commands decoding accuracy, 86.27% commands execution success, and an average latency of 0.89 seconds from receiving the participants' vocal chat commands to initiating the robot's actual physical action. The video demonstrations of this paper can be found at https://linusnep.github.io/MTCC-IRoNL/.

M2CURL: Sample-Efficient Multimodal Reinforcement Learning via Self-Supervised Representation Learning for Robotic Manipulation

One of the most critical aspects of multimodal Reinforcement Learning (RL) is the effective integration of different observation modalities. Having robust and accurate representations derived from these modalities is key to enhancing the robustness and sample efficiency of RL algorithms. However, learning representations in RL settings for visuotactile data poses significant challenges, particularly due to the high dimensionality of the data and the complexity involved in correlating visual and tactile inputs with the dynamic environment and task objectives. To address these challenges, we propose Multimodal Contrastive Unsupervised Reinforcement Learning (M2CURL). Our approach employs a novel multimodal self-supervised learning technique that learns efficient representations and contributes to faster convergence of RL algorithms. Our method is agnostic to the RL algorithm, thus enabling its integration with any available RL algorithm. We evaluate M2CURL on the Tactile Gym 2 simulator and we show that it significantly enhances the learning efficiency in different manipulation tasks. This is evidenced by faster convergence rates and higher cumulative rewards per episode, compared to standard RL algorithms without our representation learning approach.

Integrating Human Expertise in Continuous Spaces: A Novel Interactive Bayesian Optimization Framework with Preference Expected Improvement

Interactive Machine Learning (IML) seeks to integrate human expertise into machine learning processes. However, most existing algorithms cannot be applied to Realworld Scenarios because their state spaces and/or action spaces are limited to discrete values. Furthermore, the interaction of all existing methods is restricted to deciding between multiple proposals. We therefore propose a novel framework based on Bayesian Optimization (BO). Interactive Bayesian Optimization (IBO) enables collaboration between machine learning algorithms and humans. This framework captures user preferences and provides an interface for users to shape the strategy by hand. Additionally, we've incorporated a new acquisition function, Preference Expected Improvement (PEI), to refine the system's efficiency using a probabilistic model of the user preferences. Our approach is geared towards ensuring that machines can benefit from human expertise, aiming for a more aligned and effective learning process. In the course of this work, we applied our method to simulations and in a real world task using a Franka Panda robot to show human-robot collaboration.

The Conversation is the Command: Interacting with Real-World Autonomous Robot Through Natural Language

In recent years, autonomous agents have surged in real-world environments such as our homes, offices, and public spaces. However, natural human-robot interaction remains a key challenge. In this paper, we introduce an approach that synergistically exploits the capabilities of large language models (LLMs) and multimodal vision-language models (VLMs) to enable humans to interact naturally with autonomous robots through conversational dialogue. We leveraged the LLMs to decode the high-level natural language instructions from humans and abstract them into precise robot actionable commands or queries. Further, we utilised the VLMs to provide a visual and semantic understanding of the robot's task environment. Our results with 99.13% command recognition accuracy and 97.96% commands execution success show that our approach can enhance human-robot interaction in real-world applications. The video demonstrations of this paper can be found at https://osf.io/wzyf6 and the code is available at our GitHub repository (https://github.com/LinusNEP/TCC_IRoNL.git).

Multimodal Visual-Tactile Representation Learning through Self-Supervised Contrastive Pre-Training

The rapidly evolving field of robotics necessitates methods that can facilitate the fusion of multiple modalities. Specifically, when it comes to interacting with tangible objects, effectively combining visual and tactile sensory data is key to understanding and navigating the complex dynamics of the physical world, enabling a more nuanced and adaptable response to changing environments. Nevertheless, much of the earlier work in merging these two sensory modalities has relied on supervised methods utilizing datasets labeled by humans.This paper introduces MViTac, a novel methodology that leverages contrastive learning to integrate vision and touch sensations in a self-supervised fashion. By availing both sensory inputs, MViTac leverages intra and inter-modality losses for learning representations, resulting in enhanced material property classification and more adept grasping prediction. Through a series of experiments, we showcase the effectiveness of our method and its superiority over existing state-of-the-art self-supervised and supervised techniques. In evaluating our methodology, we focus on two distinct tasks: material classification and grasping success prediction. Our results indicate that MViTac facilitates the development of improved modality encoders, yielding more robust representations as evidenced by linear probing assessments.

CR-VAE: Contrastive Regularization on Variational Autoencoders for Preventing Posterior Collapse

The Variational Autoencoder (VAE) is known to suffer from the phenomenon of \textit{posterior collapse}, where the latent representations generated by the model become independent of the inputs. This leads to degenerated representations of the input, which is attributed to the limitations of the VAE's objective function. In this work, we propose a novel solution to this issue, the Contrastive Regularization for Variational Autoencoders (CR-VAE). The core of our approach is to augment the original VAE with a contrastive objective that maximizes the mutual information between the representations of similar visual inputs. This strategy ensures that the information flow between the input and its latent representation is maximized, effectively avoiding posterior collapse. We evaluate our method on a series of visual datasets and demonstrate, that CR-VAE outperforms state-of-the-art approaches in preventing posterior collapse.

Understanding why SLAM algorithms fail in modern indoor environments

Simultaneous localization and mapping (SLAM) algorithms are essential for the autonomous navigation of mobile robots. With the increasing demand for autonomous systems, it is crucial to evaluate and compare the performance of these algorithms in real-world environments. In this paper, we provide an evaluation strategy and real-world datasets to test and evaluate SLAM algorithms in complex and challenging indoor environments. Further, we analysed state-of-the-art (SOTA) SLAM algorithms based on various metrics such as absolute trajectory error, scale drift, and map accuracy and consistency. Our results demonstrate that SOTA SLAM algorithms often fail in challenging environments, with dynamic objects, transparent and reflecting surfaces. We also found that successful loop closures had a significant impact on the algorithm's performance. These findings highlight the need for further research to improve the robustness of the algorithms in real-world scenarios.

O2S: Open-source open shuttle

Currently, commercially available intelligent transport robots that are capable of carrying up to 90kg of load can cost \$5000 or even more. This makes real-world experimentation prohibitively expensive and limits the applicability of such systems to everyday home or industrial tasks. Aside from their high cost, the majority of commercially available platforms are either closed-source, platform-specific or use difficult-to-customize hardware and firmware. In this work, we present a low-cost, open-source and modular alternative, referred to herein as "open-source open shuttle (O2S)". O2S utilizes off-the-shelf (OTS) components, additive manufacturing technologies, aluminium profiles, and a consumer hoverboard with high-torque brushless direct current (BLDC) motors. O2S is fully compatible with the robot operating system (ROS), has a maximum payload of 90kg, and costs less than $1500. Furthermore, O2S offers a simple yet robust framework for contextualizing simultaneous localization and mapping (SLAM) algorithms, an essential prerequisite for autonomous robot navigation. The robustness and performance of the O2S were validated through real-world and simulation experiments. All the design, construction and software files are freely available online under the GNU GPL v3 license at https://doi.org/10.17605/OSF.IO/K83X7. A descriptive video of O2S can be found at https://osf.io/v8tq2.