Modern incarnations of tactile sensors produce high-dimensional raw sensory feedback such as images, making it challenging to efficiently store, process, and generalize across sensors. To address these concerns, we introduce a novel implicit function representation for tactile sensor feedback. Rather than directly using raw tactile images, we propose neural implicit functions trained to reconstruct the tactile dataset, producing compact representations that capture the underlying structure of the sensory inputs. These representations offer several advantages over their raw counterparts: they are compact, enable probabilistically interpretable inference, and facilitate generalization across different sensors. We demonstrate the efficacy of this representation on the downstream task of in-hand object pose estimation, achieving improved performance over image-based methods while simplifying downstream models. We release code, demos and datasets at https://www.mmintlab.com/tactile-functasets.

Magnetic anomaly detection (MAD) using vector magnetometers is extensively applied in ship detection, vehicle tracking, oil pipeline localization, and unexploded ordnance (UXO) detection. However, inherent magnetometer errors and platform-induced errors significantly limit detection performance. Interference compensation aims to mitigate these effects and enhance detection accuracy. Insufficient compensation data often lead to divergence issues. To address this, we propose an online compensation method employing recursive singular value decomposition (RSVD). This approach provides robust parameter estimation, effectively mitigates online interference even with limited data, and automatically reduces the number of effective singular values to enhance compensation accuracy. Through three experiments, we validate the algorithm’s effectiveness. The RSVD-based compensation method demonstrates excellent magnetic interference suppression and target detection performance under both sufficient and insufficient data conditions. In an offshore test, the peak-to-peak interference value before compensation was 285.6 nT, and compensation using recursive least squares (RLS) was failed. After compensation, the interference values using the Kalman and RSVD methods were 9.3 and 4.6 nT, respectively. Furthermore, previously undetectable MAD signals became discernible after compensation, with peak-to-peak values of 4.8 (Kalman) and 70.9 nT (RSVD). The RSVD-based compensation method performs significantly better in MAD experiments.

Zero-Shot Object Navigation (ZSON) enables agents to navigate towards open-vocabulary objects in unknown environments. The existing works of ZSON mainly focus on following individual instructions to find generic object classes, neglecting the utilization of natural language interaction and the complexities of identifying user-specific objects. To address these limitations, we introduce Zero-shot Interactive Personalized Object Navigation (ZIPON), where robots need to navigate to personalized goal objects while engaging in conversations with users. To solve ZIPON, we propose a new framework termed Open-woRld Interactive persOnalized Navigation (ORION)1, which uses Large Language Models (LLMs) to make sequential decisions to manipulate different modules for perception, navigation and communication. Experimental results show that the performance of interactive agents that can leverage user feedback exhibits significant improvement. However, obtaining a good balance between task completion and the efficiency of navigation and interaction remains challenging for all methods. We further provide more findings on the impact of diverse user feedback forms on the agents’ performance.