The household rearrangement task involves spotting misplaced objects in a scene and accommodate them with proper places. It depends both on common-sense knowledge on the objective side and human user preference on the subjective side. In achieving such a task, we propose to mine object functionality with user preference alignment directly from the scene itself, without relying on human intervention. To do so, we work with scene graph representation and propose LLM-enhanced scene graph learning which transforms the input scene graph into an Affordance Enhanced Graph (AEG) with information-enriched nodes and newly discovered edges (relations). In AEG, the nodes corresponding to the receptacle objects are augmented with context-induced affordance which encodes what kind of carriable objects can be placed on it. New edges are discovered with newly discovered non-local relations. With AEG, we perform task planning for scene rearrangement by detecting misplaced carriables and determining a proper placement for each of them. We implement an end-to-end robot system for autonomous household rearrangement in unseen environments and test our method by implementing a tiding robot in both simulated environments and real-world scenarios, and perform evaluation on a new benchmark we build. Extensive evaluations demonstrate that our method achieves state-of-the-art performance in misplacement detection and rearrangement planning.

Object goal navigation (ObjectNav) is a fundamental task in embodied AI, requiring an agent to locate a target object in previously unseen environments. This task is particularly challenging because it requires both perceptual and cognitive processes, including object recognition and decision-making. While substantial advancements in perception have been driven by the rapid development of visual foundation models, progress on the cognitive aspect remains constrained, primarily limited to either implicit learning through simulator rollouts or explicit reliance on predefined heuristic rules. Inspired by neuroscientific findings demonstrating that humans maintain and dynamically update fine-grained cognitive states during object search tasks in novel environments, we propose CogNav, a framework designed to mimic this cognitive process using large language models. Specifically, we model the cognitive process using a finite state machine comprising fine-grained cognitive states, ranging from exploration to identification. Transitions between states are determined by a large language model based on a dynamically constructed heterogeneous cognitive map, which contains spatial and semantic information about the scene being explored. Extensive evaluations on the HM3D, MP3D, and RoboTHOR benchmarks demonstrate that our cognitive process modeling significantly improves the success rate of ObjectNav at least by relative 14% over the state-of-the-arts.

This paper presents a 2–20-GHz highly accurate vector-sum variable gain phase shifter (VGPS) monolithic microwave integrated circuit (MMIC) for ultra-broadband phased-array applications. An active power splitter followed by a dual-path I/Q network is utilized for precise I/Q signals generation. A reverse-slope phase compensation technique is proposed to improve broadband I/Q phase balances. Two active single-to-differential convertors further divide the I/Q signals into four quadrature signals. The vector modulator consisting of variable gain amplifiers (VGAs), passive analog adder and differential-to-single convertor synthesizes the desired output phase with tunable gain by orthogonal modulation and summation of the four quadrature signals. The designed VGPS, fabricated in 0.25-$\mu \text{m}$GaAs pHEMT technology, achieves 360° of full-span phase shift with tunable gain and a one-decade instantaneous bandwidth. Measurement result shows that the peak gain and input referred 1-dB compression point of the proposed VGPS are–3.1-dB and +6.5-dBm, respectively. With the aid of off-chip frequency-independent logic circuits and digital-to-analog convertor (DAC), the VGPS exhibits 6-bit phase resolution with root-mean-square (RMS) phase error of less than 2.92°over 2–20-GHz. The VGPS also results in a 4-bit gain control performance with 7.5-dB gain tuning range (RMS gain error < 0.34-dB) and a 5-bit gain control performance with 15.5-dB gain tuning range (RMS gain error < 0.62-dB). The VGPS MMIC consumes 115-mA current from a 5-V voltage supply and occupies chip area of 4.5-mm2 (excluding pads).

We introduce MIPS-Fusion, a robust and scalable online RGB-D reconstruction method based on a novel neural implicit representation - multi-implicit-submap. Different from existing neural RGB-D reconstruction methods lacking either flexibility with a single neural map or scalability due to extra storage of feature grids, we propose a pure neural representation tackling both difficulties with a divide-and-conquer design. In our method, neural submaps are incrementally allocated alongside the scanning trajectory and efficiently learned with local neural bundle adjustments. The submaps can be refined individually in a back-end optimization and optimized jointly to realize submap-level loop closure. Meanwhile, we propose a hybrid tracking approach combining randomized and gradient-based pose optimizations. For the first time, randomized optimization is made possible in neural tracking with several key designs to the learning process, enabling efficient and robust tracking even under fast camera motions. The extensive evaluation demonstrates that our method attains higher reconstruction quality than the state of the arts for large-scale scenes and under fast camera motions.