– Overview Motion planning is a fundamental problem in robotics. It may be stated as finding a path for a robot or agent, such that the robot or agent may move along this path from its initial configuration to goal configuration without colliding with any static obstacles or other robots or agents in the environment. Motion planning algorithms are used in many fields, including bioinformatics, character animation, computer-aided design and computer-aided manufacturing (CAD/CAM), industrial automation, robotic surgery, and single and multiple robot navigation in both two and three dimensions.
Abstract We present a centralized algorithm for labeled, disk-shaped Multi-Robot Path Planning (MPP) in a continuous planar workspace with polygonal boundaries. Our method automatically transform the continuous problem into a discrete, graph-based variant termed the pebble motion problem, which can be solved efficiently. To construct the underlying pebble-graph, we identify inscribed circles in the workspace via a medial axis transform and organize robots into layers within each inscribed circle. We show that our layered pebble-graph enables collision-free motions, allowing all graph-restricted MPP instances to be feasible.
Abstract Automatic emotion recognition plays a key role in computer-human interaction as it has the potential to enrich the next-generation artificial intelligence with emotional intelligence. It finds applications in customer and/or representative behavior analysis in call centers, gaming, personal assistants, and social robots, to mention a few. Therefore, there has been an increasing demand to develop robust automatic methods to analyze and recognize the various emotions. In this paper, we propose a neural network-based emotion recognition framework that uses a late fusion of transfer-learned and fine-tuned models from speech and text modalities.
Abstract We present a robust learning algorithm to detect and handle collisions in 3D deforming meshes. We first train a neural network to detect collisions and then use a numerical optimization algorithm to resolve penetrations guided by the network. Our learned collision handler can resolve collisions for unseen, high-dimensional meshes with thousands of vertices. To obtain stable network performance in such large and unseen spaces, we apply active learning by progressively inserting new collision data based on the network inferences.
Overview Many powerful machine learning algorithms have been developed that are very successful, but which are “black boxes,” in that these models are often inscrutable as to their inner logic, or at least require significant analysis to penetrate. Thus, there is a growing interest in Explainable Artificial Intelligence (XAI) and an increasing body of work focusing on explainability and interpretability in deep learning and reinforcement learning.
Abstract We present a novel learning-based modal sound synthesis approach that includes a mixed vibration solver for modal analysis and an end-to-end sound radiation network for acoustic transfer. Our mixed vibration solver consists of a 3D sparse convolution network and a Locally Optimal Block Preconditioned Conjugate Gradient module (LOBPCG) for iterative optimization. Moreover, we highlight the correlation between a standard modal vibration solver and our network architecture. Our radiation network predicts the Far-Field Acoustic Transfer maps (FFAT Maps) from the surface vibration of the object.
Abstract We present a modified velocity-obstacle (VO) algorithm that uses probabilistic partial observations of the environment to compute velocities and navigate a robot to a target. Our system uses commodity visual sensors, including a mono-camera and a 2D Lidar, to explicitly predict the velocities and positions of surrounding obstacles through optical flow estimation, object detection, and sensor fusion. A key aspect of our work is coupling the perception (OF: optical flow) and planning (VO) components for reliable navigation.
– Overview A common method to understand policies of RL agents that operate on a visual space is to just watch it act. Working with RL policies based on non-visual sensor data poses a unique problem though, because humans are unable to evaluate it. This motivates us to create the novel OccupancyViz library. It allows human-interpretable real time visualization of the polar occupancy grid portions of states that the RL agent takes as input, and their corresponding actions.
Abstract We present PACE, a novel method for modifying motion-captured virtual agents to interact with and move throughout dense, cluttered 3D scenes. Our approach changes a given motion sequence of a virtual agent as needed to adjust to the obstacles and objects in the environment. We first take the individual frames of the motion sequence most important for modeling interactions with the scene and pair them with the relevant scene geometry, obstacles, and semantics such that interactions in the agents motion match the affordances of the scene (e.