Abstract: A robotic system is provided for performing rearrangement tasks guided by a natural language instruction. The system can include a number of neural networks used to determine a selected rearrangement of the objects in accordance with the natural language instruction. A target object predictor network processes a point cloud of the scene and the natural language instruction to identify a set of query objects that are to-be-rearranged. A language conditioned prior network processes the point cloud, natural language instruction, and the set of query objects to sample a distribution of rearrangements to generate a number of sets of pose offsets for the set of query objects. A discriminator network then processes the samples to generate scores for the samples. The samples may be refined until a score for at least one of the sample generated by the discriminator network is above a threshold value.

Abstract: In various examples, 3D object knowledge can be developed to extract diverse knowledge from large language models, and a part-grounding model can be trained to ground part semantics in terms of local shape features and spatial relations between parts. For example, knowledge that “the opening part of a mug that affords the pouring action is located on the top of the mug body and is often circular” can be grounded by identifying a previously unknown “opening” part based on its spatial relation to the known “body” part and its circular shape. A robotic system, for example, may use a model to identify an unlabeled part of a 3D object in imaging data. The model may be generated using natural language descriptions of relationships between parts of 3D objects, with descriptions generated using a language model that produces text in response to queries related to spatial relationships between the parts.

Abstract: A robotic system is provided for performing rearrangement tasks guided by a natural language instruction. The system can include a number of neural networks used to determine a selected rearrangement of the objects in accordance with the natural language instruction. A target object predictor network processes a point cloud of the scene and the natural language instruction to identify a set of query objects that are to-be-rearranged. A language conditioned prior network processes the point cloud, natural language instruction, and the set of query objects to sample a distribution of rearrangements to generate a number of sets of pose offsets for the set of query objects. A discriminator network then processes the samples to generate scores for the samples. The samples may be refined until a score for at least one of the sample generated by the discriminator network is above a threshold value.

Abstract: A method for supporting multi audio tracks in wireless communication field, which uses multi stream media servers to share the assignment for supporting multi audio tracks. One stream media server receives one video data and multi audio data, but outputs only one determinate audio data; or one stream media server receives one video data and one audio data from multi audio data. User can select the required language by using portal website, and then connect to the stream media server for obtaining one video data and one audio data. The invention also provides a stream media server and a system for supporting multi audio tracks.