Browsing by Author "Naderi, Kourosh"
Now showing 1 - 7 of 7
Results Per Page
Sort Options
Item Computer-aided imagery in sport and exercise: A case study of indoor wall climbing(2018-01-01) Naderi, Kourosh; Takatalo, Jari; Lipsanen, Jari; Hämäläinen, Perttu; Department of Computer Science; Department of Media; Professorship Hämäläinen Perttu; University of HelsinkiMovement artificial intelligence of simulated humanoid characters has been advancing rapidly through joint efforts of the computer animation, robotics, and machine learning communitites. However, practical real-life applications are still rare. We propose applying the technology to mental practice in sports, which we denote as computer-aided imagery (CAI). Imagery, i.e., rehearsing the task in one's mind, is a difficult cognitive skill that requires accurate mental simulation; we present a novel interactive computational sport simulation for exploring and planning movements and strategies. We utilize a fully physically-based avatar with motion optimization that is not limited by a movement dataset, and customize the avatar with computer vision measurements of user's body. We evaluate the approach with 20 users in preparing for real-life wall climbing. Our results indicate that the approach is promising and can affect body awareness and feelings of competence. However, more research is needed to achieve accurate enough simulation for both gross-motor body movements and fine-motor control of the myriad ways in which climbers can grasp climbing holds or shapes.Item Discovering and synthesizing humanoid climbing movements(ASSOC COMPUTING MACHINERY, 2017) Naderi, Kourosh; Rajamäki, Joose; Hämäläinen, Perttu; Department of Computer Science; Professorship Hämäläinen PerttuThis paper addresses the problem of offline path and movement planning for wall climbing humanoid agents. We focus on simulating bouldering, i.e. climbing short routes with diverse moves, although we also demonstrate our system on a longer wall. Our approach combines a graph-based highlevel path planner with low-level sampling-based optimization of climbing moves. Although the planning problem is complex, our system produces plausible solutions to bouldering problems (short climbing routes) in less than a minute. We further utilize a k-shortest paths approach, which enables the system to discover alternative paths - in climbing, alternative strategies often exist, and what might be optimal for one climber could be impossible for others due to individual differences in strength, flexibility, and reach. We envision our system could be used, e.g. in learning a climbing strategy, or as a test and evaluation tool for climbing route designers. To the best of our knowledge, this is the first paper to solve and simulate rich humanoid wall climbing, where more than one limb can move at the same time, and limbs can also hang free for balance or use wall friction in addition to predefned holds.Item Discovering, Synthesizing, and Learning Climbing Movements(Aalto University, 2020) Naderi, Kourosh; Kyrki, Ville, Prof., Aalto University, Department of Electrical Engineering and Automation, Finland; Tietotekniikan laitos; Department of Computer Science; Aalto Game Research Group; Perustieteiden korkeakoulu; School of Science; Hämäläinen, Perttu, Prof, Aalto University, Department of Computer Science, FinlandAlthough animation is commonly captured from real humans or edited manually through keyframes and interpolation curves, such techniques are time-consuming and expensive. Because of this, a long-standing goal of computer animation research has been to synthesize movements algorithmically, e.g., through simulating the human biomechanics and framing the animation problem as optimization of joint torques over time. During recent years, such approaches have enjoyed success with movements like bipedal locomotion, but some complex movement skills have remained challenging. This dissertation focuses on synthesizing natural looking and human-like climbing movements in indoor bouldering, a popular and rapidly growing sport that recently was approved to the 2020 Tokyo Olympics together with speed and sport climbing. Indoor bouldering is a form of climbing that takes place relatively close to the ground on top of a soft landing surface, and does not require special equipment other than climbing shoes. Bouldering routes are usually short and they focus on complex climbing moves that require both strength and coordination. Planning and discovering the optimal or at least possible sequence of moves from the ground to the top hold is a challenging problem. The problem gets even more complicated when the planning should consider the body types of users such that the planned path and synthesized motions would be feasible for them. This thesis proposes a high-level path planner and low-level controller for synthesizing physically plausible and human-like movements. The high-level graph-based path planner is responsible for planning a sequence of movements to the top hold while the low-level controller synthesizes the movement details through optimizing the joint actuations of a physics simulation model of a humanoid climber. Such a low-level controller might fail to follow the planned movements; the thesis proposes ways to handle this uncertainty through low-level and high-level controller interaction. In subsequent work, the approach is developed further by employing neural networks in both supervised and reinforcement learning settings. The methods proposed in the thesis result in high-quality climbing animations without needing any reference animation or motion capture data. The work should also have applications in synthesizing other types of movements with similar characteristics, e.g., creating parkour animations based on desired footstep patterns.Item Generation of realistic floorplans using diffusion-based models(2023-10-09) Hahkio, Linh; Naderi, Kourosh; Perustieteiden korkeakoulu; Ilin, AlexanderExisting studies on automatic floor plan generation have been mainly focused on the room layout of the floorplans while ignoring fenestration and furniture details, which was justified by the fact that these details are often irrelevant for the user. In this thesis, we propose to generate floorplans using diffusion-based generative models trained on images that contain fenestration and furniture information. Our experiments suggest this approach results in more realistic floorplans in comparison to previous generative models such as HouseGAN++. We also show that the proposed diffusion-based generative models can be used for reconstructing missing information in existing floorplans, for example, missing labels of the room types.Item Intelligent Middle-Level Game Control(2018-08-13) Babadi, Amin; Naderi, Kourosh; Hämäläinen, Perttu; Department of Computer Science; Department of Media; Professorship Hämäläinen PerttuWe propose the concept of intelligent middle-level game control, which lies on a continuum of control abstraction levels between the following two dual opposites: 1) high-level control that translates player’s simple commands into complex actions (such as pressing Space key for jumping), and 2) low-level control which simulates real-life complexities by directly manipulating, e.g., joint rotations of the character as it is done in the runner game QWOP. We posit that various novel control abstractions can be explored using recent advances in movement intelligence of game characters. We demonstrate this through design and evaluation of a novel 2-player martial arts game prototype. In this game, each player guides a simulated humanoid character by clicking and dragging body parts. This defines the cost function for an online continuous control algorithm that executes the requested movement. Our control algorithm uses Covariance Matrix Adaptation Evolution Strategy (CMA-ES) in a rolling horizon manner with custom population seeding techniques. Our playtesting data indicates that intelligent middle-level control results in producing novel and innovative gameplay without frustrating interface complexities.Item Predicting Mid-Air Interaction Movements and Fatigue Using Deep Reinforcement Learning(2020) Cheema, Noshaba; Frey-Law, Laura A.; Naderi, Kourosh; Lehtinen, Jaakko; Slusallek, Philipp; Hämäläinen, Perttu; Department of Computer Science; Department of Media; Professorship Hämäläinen Perttu; Professorship Lehtinen Jaakko; Helsinki Institute for Information Technology (HIIT); University of Iowa; Saarland University; Max Planck Institute for InformaticsA common problem of mid-air interaction is excessive arm fatigue, known as the "Gorilla arm" effect. To predict and prevent such problems at a low cost, we investigate user testing of mid-air interaction without real users, utilizing biomechanically simulated AI agents trained using deep Reinforcement Learning (RL). We implement this in a pointing task and four experimental conditions, demonstrating that the simulated fatigue data matches human fatigue data. We also compare two effort models: 1) instantaneous joint torques commonly used in computer animation and robotics, and 2) the recent Three Compartment Controller (3CC-) model from biomechanical literature. 3CC- yields movements that are both more efficient and relaxed, whereas with instantaneous joint torques, the RL agent can easily generate movements that are quickly tiring or only reach the targets slowly and inaccurately. Our work demonstrates that deep RL combined with the 3CC- provides a viable tool for predicting both interaction movements and user experiencein silico, without users.Item A reinforcement learning approach to synthesizing climbing movements(IEEE, 2019-08-01) Naderi, Kourosh; Babadi, Amin; Roohi, Shaghayegh; Hamalainen, Perttu; Department of Computer Science; Department of Media; Professorship Hämäläinen PerttuThis paper addresses the problem of synthesizing simulated humanoid climbing movements given the target holds, e.g., by the player of a climbing game. We contribute the first deep reinforcement learning solution that can handle interactive physically simulated humanoid climbing with more than one limb switching holds at the same time. A key component of our approach is Self-Supervised Episode State Initialization (SS- ESI), which ensures diverse exploration and speeds up learning, compared to a baseline approach where the climber is reset to an initial pose after failure. Our results also show that training with a multi-step action parameterization can produce both smoother movements and enable learning from slightly fewer explored actions at the cost of increased simulation time per action.