Recent research on motion generation has shown significant progress in generating semantically aligned motion with singular semantics. However, when employing these models to create composite sequences containing multiple semantically generated motion clips, they often struggle to preserve the continuity of motion dynamics at the transition boundaries between clips, resulting in awkward transitions and abrupt artifacts. To address these challenges, we present Compositional Phase Diffusion, which leverages the Semantic Phase Diffusion Module (SPDM) and Transitional Phase Diffusion Module (TPDM) to progressively incorporate semantic guidance and phase details from adjacent motion clips into the diffusion process. Specifically, SPDM and TPDM operate within the latent motion frequency domain established by the pre-trained Action-Centric Motion Phase Autoencoder (ACT-PAE). This allows them to learn semantically important and transition-aware phase information from variable-length motion clips during training. Experimental results demonstrate the competitive performance of our proposed framework in generating compositional motion sequences that align semantically with the input conditions, while preserving phase transitional continuity between preceding and succeeding motion clips. Additionally, motion inbetweening task is made possible by keeping the phase parameter of the input motion sequences fixed throughout the diffusion process, showcasing the potential for extending the proposed framework to accommodate various application scenarios. Codes are available at https://github.com/asdryau/TransPhase.

Motion sequencing is a crucial process in creating smooth and natural animations by arranging individual motion sequences based on desired action scripts. Existing methods either rely on carefully engineered key-frame libraries or implicitly encoded latent phase manifolds for sequential interpolation and manipulation. However, ensuring smooth and natural transitions becomes challenging when dealing with complex and diverse actions, and the manipulation flexibility is limited to the frame level. In this study, we introduce a novel motion sequencing framework centered around Labanotation. The framework leverages automatically annotated Labanotation for explicit representation of motion elements to the body-part level. The proposed Laban Masked Autoencoder (LBN-MAE) is able to directly complete, interpolate and translate Laban symbols into natural 3D trajectories. Our framework offers a compact and descriptive representation of motion, enabling precise motion control and reediting. Comparative evaluations against both conventional and state-of-the-art learning-based methods validate the effectiveness of our proposed framework.

This paper presents a trajectory planning method for automated parking. The proposed method constructs a state roadmap in which each node contains not only position but also orientation information of the vehicle. The roadmap is constructed by dividing the orientation space in multiple resolutions considering the non-holonomic constraints of the vehicle and the collision-avoidance constraints between the vehicle and the boundary of the parking environment. Using the state roadmap, a complex parking trajectory composed of both forward and reverse motions can be computed with small online computation cost. The proposed method is evaluated in both numerical simulations and an experiment using an electric vehicle.

This research develops a new graph-map method for autonomous car-like mobile robots based on variable-resolution division of space. Unlike conventional roadmaps, which include position information only, the proposed graph-map also includes orientation information of the car-like robot. In this manner, the robot is able to plan a path in detail. The orientation information of each node is not a fixed value but a range. The range is constructed by dividing the orientation space using variable-resolution, which is obtained from the surrounding situation of links that connect to the node. Finally, the proposed method is evaluated through simulations.

This research addresses a method for mobile robots that simultaneously performs map building and path-planning on line. A graph representation of a workspace with variable resolutions is constructed using measurement data obtained by omni-directional distance sensors. At the same time, a real-time search for a feasible path to the goal is executed on the constructed graph-map. The proposed method is evaluated through experiments using an omni-directional mobile robot equipped with laser range finders.