Browsing by Author "Struckmeier, Oliver"

Filter results by typing the first few letters
Now showing 1 - 13 of 13
  • Autoencoding Slow Representations for Semi-supervised Data-Efficient Regression
    (2023-07) Struckmeier, Oliver; Tiwari, Kshitij; Kyrki, Ville
     A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
    The slowness principle is a concept inspired by the visual cortex of the brain. It postulates that the underlying generative factors of a quickly varying sensory signal change on a different, slower time scale. By applying this principle to state-of-the-art unsupervised representation learning methods one can learn a latent embedding to perform supervised downstream regression tasks more data efficient. In this paper, we compare different approaches to unsupervised slow representation learning such as L norm based slowness regularization and the SlowVAE, and propose a new term based on Brownian motion used in our method, the S-VAE. We empirically evaluate these slowness regularization terms with respect to their downstream task performance and data efficiency in state estimation and behavioral cloning tasks. We find that slow representations show great performance improvements in settings where only sparse labeled training data is available. Furthermore, we present a theoretical and empirical comparison of the discussed slowness regularization terms. Finally, we discuss how the Fr\'echet Inception Distance (FID), commonly used to determine the generative capabilities of GANs, can predict the performance of trained models in supervised downstream tasks.
  • Autonomous Generation of Robust and Focused Explanations for Robot Policies
    (2019-10-01) Struckmeier, Oliver; Racca, Mattia; Kyrki, Ville
     A4 Artikkeli konferenssijulkaisussa
    Transparency of robot behaviors increases efficiency and quality of interactions with humans. To increase transparency of robot policies, we propose a method for generating robust and focused explanations that express why a robot chose a particular action. The proposed method examines the policy based on the state space in which an action was chosen and describes it in natural language. The method can generate focused explanations by leaving out irrelevant state dimensions, and avoid explanations that are sensitive to small perturbations or have ambiguous natural language concepts. Furthermore, the method is agnostic to the policy representation and only requires the policy to be evaluated at different samples of the state space. We conducted a user study with 18 participants to investigate the usability of the proposed method compared to a comprehensive method that generates explanations using all dimensions. We observed how focused explanations helped the subjects more reliably detect the irrelevant dimensions of the explained system and how preferences regarding explanation styles and their expected characteristics greatly differ among the participants.
  • Bio-inspired robotic haptic exploration
    (2019-05-20) Suomela, Minka
     Sähkötekniikan korkeakoulu | Bachelor's thesis
  • Deep state-space models: combining deep learning and Bayesian filtering.
    (2020-08-26) Reinikka, Paavo
     Sähkötekniikan korkeakoulu | Bachelor's thesis
  • Domain Curiosity: Learning Efficient Data Collection Strategies for Domain Adaptation
    (2021-12-16) Arndt, Karol; Struckmeier, Oliver; Kyrki, Ville
     A4 Artikkeli konferenssijulkaisussa
    Domain adaptation is a common problem in robotics, with applications such as transferring policies from simulation to real world and lifelong learning. Performing such adaptation, however, requires informative data about the environment to be available during the adaptation. In this paper, we present domain curiosity—a method of training exploratory policies that are explicitly optimized to provide data that allows a model to learn about the unknown aspects of the environment. In contrast to most curiosity methods, our approach explicitly rewards learning, which makes it robust to environment noise without sacrificing its ability to learn. We evaluate the proposed method by comparing how much a model can learn about environment dynamics given data collected by the proposed approach, compared to standard curious and random policies. The evaluation is performed using a toy environment, two simulated robot setups, and on a real-world haptic exploration task. The results show that the proposed method allows data-efficient and accurate estimation of dynamics.
  • Explainable Human-Robot Interaction to Form Precise Mental Models in Humans
    (2020-05-05) Eklund, Anton
     Sähkötekniikan korkeakoulu | Bachelor's thesis
  • Generating Explanations of Robot Policies in Continuous State Spaces
    (2018-08-20) Struckmeier, Oliver
     Sähkötekniikan korkeakoulu | Master's thesis
    Transparency in HRI describes the method of making the current state of a robot or intelligent agent understandable to a human user. Applying transparency mechanisms to robots improves the quality of interaction as well as the user experience. Explanations are an effective way to make a robot’s decision making transparent. We introduce a framework that uses natural language labels attached to a region in the continuous state space of the robot to automatically generate local explanations of a robot’s policy. We conducted a pilot study and investigated how the generated explanations helped users to understand and reproduce a robot policy in a debugging scenario.
  • Imitation Learning to Create Human-like AI for Video games
    (2023-05-26) Sauramäki, Joona
     Sähkötekniikan korkeakoulu | Bachelor's thesis
  • Multimodal Representation Learning for Place Recognition Using Deep Hebbian Predictive Coding
    (2021-12-13) Pearson, Martin J.; Dora, Shirin; Struckmeier, Oliver; Knowles, Thomas C.; Mitchinson, Ben; Tiwari, Kshitij; Kyrki, Ville; Bohte, Sander; Pennartz, Cyriel M.A.
     A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä
    Recognising familiar places is a competence required in many engineering applications that interact with the real world such as robot navigation. Combining information from different sensory sources promotes robustness and accuracy of place recognition. However, mismatch in data registration, dimensionality, and timing between modalities remain challenging problems in multisensory place recognition. Spurious data generated by sensor drop-out in multisensory environments is particularly problematic and often resolved through adhoc and brittle solutions. An effective approach to these problems is demonstrated by animals as they gracefully move through the world. Therefore, we take a neuro-ethological approach by adopting self-supervised representation learning based on a neuroscientific model of visual cortex known as predictive coding. We demonstrate how this parsimonious network algorithm which is trained using a local learning rule can be extended to combine visual and tactile sensory cues from a biomimetic robot as it naturally explores a visually aliased environment. The place recognition performance obtained using joint latent representations generated by the network is significantly better than contemporary representation learning techniques. Further, we see evidence of improved robustness at place recognition in face of unimodal sensor drop-out. The proposed multimodal deep predictive coding algorithm presented is also linearly extensible to accommodate more than two sensory modalities, thereby providing an intriguing example of the value of neuro-biologically plausible representation learning for multimodal navigation.
  • Representation learning methods for robotic perception and learning — at the intersection of computational neuroscience and machine learning
    (2024) Struckmeier, Oliver
     School of Electrical Engineering | Doctoral dissertation (article-based)
    Despite the progress made in artificial intelligence and robotics, researchers have yet to fully decode or replicate the mechanisms behind the remarkable ability of the human brain to extract effective and flexible representations from sensor stimuli. Although numerous established machine-learning methods claim inspiration from the brain, uncovering novel concepts from neuroscience can enable further progress in robotics and machine learning. Therefore, this thesis presents research at the intersection of machine learning, robotics, and neuroscience, with an emphasis on representation learning, and perception.  First, the thesis introduces work on learning linearly alignable representations using a coupled autoencoder setup. Learning such representations simplifies the computationally demanding task of comparing and aligning probability distributions, a core component of many machine learning methods. Empirical evaluation of the proposed approach demonstrates that it can significantly simplify the solution to the mathematical optimization problem underlying domain adaptation. The core of the thesis focuses on applying principles from neuroscience to improve state-of-the-art representation learning methods. Hand-crafted features and representations learned using multi-modal variational autoencoders and predictive coding are empirically compared in terms of their robustness and data efficiency in navigation and place-recognition tasks in various experiments. Following the superior performance of predictive coding in the performed experiments, this thesis presents a brain-inspired extension to the variational autoencoder framework. Enforcing a slowness prior on latent dynamics in the variational autoencoder facilitates data-efficiency in downstream tasks. Finally, we extend our findings from the domain of representation learning and perception to imitation learning. In the constraint setting of learning from observations only, existing methods are brittle and fail to recover the causal effects of expert actions when access to the target environment is limited. Applying the previously discussed brain-inspired principles to learn representations in state-action spaces solves this problem.  The results of the research presented in this thesis indicate that augmenting representation learning methods with principles from neuroscience can help build more data-efficient, robust, and flexible intelligent systems.
  • Slowness and Disentanglement in Unsupervised Representation Learning from Temporal Data
    (2021-05-16) Tuomisto, Jaakko
     Sähkötekniikan korkeakoulu | Bachelor's thesis
  • ViTa-SLAM: A Bio-inspired Visuo-Tactile SLAM for Navigation while Interacting with Aliased Environments
    (2019-09) Struckmeier, Oliver; Tiwari, Kshitij; Salman, Mohammed; Pearson, Martin J.; Kyrki, Ville
     A4 Artikkeli konferenssijulkaisussa
    RatSLAM is a rat hippocampus-inspired visual Simultaneous Localization and Mapping (SLAM) framework capable of generating semi-metric topological representations of indoor and outdoor environments. Whisker-RatSLAM is a 6D extension of the RatSLAM and primarily focuses on object recognition by generating point clouds of objects based on tactile information from an array of biomimetic whiskers. This paper introduces a novel extension to both former works that is referred to as ViTa-SLAM that harnesses both vision and tactile information for performing SLAM. This not only allows the robot to perform natural interactions with the environment whilst navigating, as is normally seen in nature, but also provides a mechanism to fuse non-unique tactile and unique visual data. Compared to the former works, our approach can handle ambiguous scenes in which one sensor alone is not capable of identifying false-positive loop-closures.
  • Win probability estimation for strategic decision-making in esports
    (2024-08-26) Jalovaara, Perttu
     School of Science | Master's thesis
    Esports, i.e., the competitive practice of video games, has grown significantly during the past decade, giving rise to esports analytics, a subfield of sports analytics. Due to the digital nature of esports, esports analytics benefits from easier data collection compared to its physical predecessor. However, strategy optimization, one of the focal points of sports analytics, remains relatively unexplored in esports. In traditional sports analytics, win probability estimation has been used for decades to evaluate players and support strategic decision-making. This thesis explores the use of win probability estimation in esports, focusing specifically on League of Legends (LoL), one of the most popular esports games in the world. The objective of this thesis is to formalize win probability added, i.e., the change in win probability associated with a certain action, as a contextualized measure of value for strategic decision-making, using mathematical notation appropriate for contemporary esports. The proposed method is elaborated by applying it to the evaluation of items, a strategic problem in LoL. To this end, we train a deep neural network to estimate the win probability at any given LoL game state. This in-game win probability model is then benchmarked against similar models.