Jamison Heard

The integration of human–robot teams is increasingly essential in dynamic task environments, particularly in sectors like warehouse management, assembly lines, search and rescue operations, material handling, and autonomous driving. This trend leverages the complementary strengths of humans and robots to enhance efficiency and tackle complex objectives. However, significant challenges arise due to differences in task execution, communication modes, empathy, mental model understanding, and adaptability between humans and robots. This survey article examines the complexities of human–robot collaboration (HRC), focusing on the “3Cs” of teamwork: collaboration, communication, and cognition. It introduces a novel 3Cs rating system to evaluate HRC systems, offering a comprehensive analysis of current research trends and identifying key challenges. The findings highlight a prevalent lack of robot adaptation based on human states and performance, underscoring the need for improved communication metrics and consistent definitions of collaborative frameworks. Key contributions include the development of the 3Cs rating system, an in-depth analysis of HRC research trends, and the identification of critical areas requiring further investigation to realize the full potential of human–robot teams. This article aims to guide future research and development, promoting more effective human–robot collaborations.

Biological and psychological concepts have inspired reinforcement learning algorithms to create new complex behaviors that expand agents' capacity. These behaviors can be seen in the rise of techniques like goal decomposition, curriculum, and intrinsic rewards, which have paved the way for these complex behaviors. One limitation in evaluating these methods is the requirement for engineered extrinsic for realistic environments. A central challenge in engineering the necessary reward function(s) comes from these environments containing states that carry high negative rewards, but provide no feedback to the agent. Death is one such stimuli that fails to provide direct feedback to the agent. In this work, we introduce an intrinsic reward function inspired by early amygdala development and produce this intrinsic reward through a novel memory-augmented neural network (MANN) architecture. We show how this intrinsic motivation serves to deter exploration of terminal states and results in avoidance behavior similar to fear conditioning observed in animals. Furthermore, we demonstrate how modifying a threshold where the fear response is active produces a range of behaviors that are described under the paradigm of general anxiety disorders (GADs). We demonstrate this behavior in the Miniworld Sidewalk environment, which provides a partially observable Markov decision process (POMDP) and a sparse reward with a non-descriptive terminal condition, i.e., death. In effect, this study results in a biologically-inspired neural architecture and framework for fear conditioning paradigms; we empirically demonstrate avoidance behavior in a constructed agent that is able to solve environments with non-descriptive terminal conditions.

Effective human–robot collaboration (HRC) requires robots to understand and adapt to humans' psychological states. This research presents a novel approach to quantitatively measure human comfort levels during HRC through the development of two metrics: a comfortability index (CI) and an uncomfortability index (UnCI). We conducted HRC experiments where participants performed assembly tasks while the robot's behavior was systematically varied. Participants' subjective responses (including surprise, anxiety, boredom, calmness, and comfortability ratings) were collected alongside physiological signals, including electrocardiogram, galvanic skin response, and pupillometry data. We propose two novel approaches for estimating CI/UnCI: an adaptation of the emotion circumplex model that maps comfort levels to the arousal–valence space, and a kernel density estimation model trained on physiological data. Time-domain features were extracted from the physiological signals and used to train machine learning models for real-time comfort levels estimation. Our results demonstrate that the proposed approaches can effectively estimate human comfort levels from physiological signals alone, with the circumplex model showing particular promise in detecting high discomfort states. This work enables real-time measurement of human comfort during HRC, providing a foundation for developing more adaptive and human-aware collaborative robots.

While Convolutional Neural Networks (CNNs) excel at learning complex latent-space representations, their over-parameterization can lead to overfitting and reduced performance, particularly with limited data. This, alongside their high computational and memory demands, limits the applicability of CNNs for edge deployment and applications where computational resources are constrained. Low-rank matrix approximation has emerged as a promising approach to reduce CNN parameters, but existing methods often require pre-determined ranks or involve complex post-training adjustments, leading to challenges in rank selection, performance loss, and limited practicality in resource-constrained environments. This underscores the need for an adaptive compression method that integrates into the training process, dynamically adjusting model complexity based on data and task requirements. To address this, we propose an efficient training method for CNN compression via dynamic parameter rank pruning. Our approach integrates efficient matrix factorization and novel regularization techniques, forming a robust framework for dynamic rank pruning and model compression. By using Singular Value Decomposition (SVD) to model low-rank convolutional filters and dense weight matrices, and training the SVD factors with back-propagation in an end-to-end manner, we achieve model compression. We evaluate our method on modern CNNs, including ResNet-18, ResNet-20, and ResNet-32, using datasets like CIFAR-10, CIFAR-100, and ImageNet (2012). Our experiments demonstrate that the proposed method can reduce model parameters by up to 50% and improve classification accuracy by up to 2% over baseline models, making CNNs more feasible for practical applications.

Generative Adversarial Networks (GANs) have gained considerable attention owing to their impressive ability to generate high-quality, realistic images from a desired data distribution. This research introduces advancements in GANs by developing an improved activation function, a novel training strategy, and an adaptive rank decomposition method to compress the network. The proposed activation function, called Parametric Mish (PMish), automatically adjusts a trainable parameter to control the smoothness and shape of the activation function. Our method employs a Neural Architecture Search (NAS) to discover the optimal architecture for image generation while using the Maximum Mean Discrepancy (MMD) repulsive loss for adversarial training. The proposed novel training strategy improves performance by progressively increasing the upper bound of the bounded MMD-GAN repulsive loss. Finally, the proposed Adaptive Rank Decomposition (ARD) method reduces the complexity of the network with minimal impact on its generative performance, thus enabling efficient deployment on resource-limited platforms. The effectiveness of these advancements is rigorously tested on standard benchmark datasets such as CIFAR-10, CIFAR-100, STL-10, and CelebA, where significant improvements over existing techniques are demonstrated. The implementation code is available at: https://github.com/PrasannaPulakurthi/MMD-PMish-NAS.

Advances in robot teleoperation have enabled groundbreaking innovations in many fields, such as space exploration, healthcare, and disaster relief. The human operator's performance plays a key role in the success of any teleoperation task, with prior evidence suggesting that operator stress and workload can impact task performance. As robot teleoperation is currently deployed in safety-critical domains, it is essential to analyze how different stress and workload levels impact the operator. We are unaware of any prior work investigating how both stress and workload impact teleoperation performance. We conducted a novel study ( $n=24$ ) to jointly manipulate users' stress and workload and analyze the user's performance through objective and subjective measures. Our results indicate that, as stress increased, over 70% of our participants performed better up to a moderate level of stress; yet, the majority of participants performed worse as the workload increased. Importantly, our experimental design elucidated that stress and workload have related yet distinct impacts on task performance, with workload mediating the effects of distress on performance ( $p< .05$ ).