Abstract-- Vision-language-action (VLA) models have shown strong generalization for robotic action prediction through large-scale vision-language pretraining. However, most existing models rely solely on RGB cameras, limiting their perception and, consequently, manipulation capabilities. The core of our approach is the sensor-masked image, a unified representation that overlays spatially grounded and physically meaningful masks onto the RGB images, derived from sensors including an infrared camera, a mmWave radar, and a microphone array. This image-native unification keeps sensor input close to RGB statistics to facilitate training, provides a uniform interface across sensor hardware, and enables data-efficient learning with lightweight per-sensor projectors. Built on this, we present a multisensory vision-language-action model architecture and train the model based on an RGB-pretrained VLA backbone. We evaluate OmniVLA on challenging real-world tasks where sensor-modality perception guides the robotic manipulation. OmniVLA achieves an average task success rate of 84%, significantly outperforms both RGB-only and raw-sensor-input baseline models by 59% and 28% respectively, meanwhile showing higher learning efficiency and stronger generalization capability. Vision-language-action (VLA) models [1], [2] recently emerged as a powerful paradigm towards generalist policies for embodied AI.

Vision-based tactile sensors, through high-resolution optical measurements, can effectively perceive the geometric shape of objects and the force information during the contact process, thus helping robots acquire higher-dimensional tactile data. Vision-based tactile sensor simulation supports the acquisition and understanding of tactile information without physical sensors by accurately capturing and analyzing contact behavior and physical properties. However, the complexity of contact dynamics and lighting modeling limits the accurate reproduction of real sensor responses in simulations, making it difficult to meet the needs of different sensor setups and affecting the reliability and effectiveness of strategy transfer to practical applications. In this letter, we propose a contact-condition guided diffusion model that maps RGB images of objects and contact force data to high-fidelity, detail-rich vision-based tactile sensor images. Evaluations show that the three-channel tactile images generated by this method achieve a 60.58% reduction in mean squared error and a 38.1% reduction in marker displacement error compared to existing approaches based on lighting model and mechanical model, validating the effectiveness of our approach. The method is successfully applied to various types of tactile vision sensors and can effectively generate corresponding tactile images under complex loads. Additionally, it demonstrates outstanding reconstruction of fine texture features of objects in a Montessori tactile board texture generation task.

Estimating the location of contact is a primary function of artificial tactile sensing apparatuses that perceive the environment through touch. Existing contact localization methods use flat geometry and uniform sensor distributions as a simplifying assumption, limiting their ability to be used on 3D surfaces with variable density sensing arrays. This paper studies contact localization on an artificial skin embedded with mutual capacitance tactile sensors, arranged non-uniformly in an unknown distribution along a semi-conical 3D geometry. A fully connected neural network is trained to localize the touching points on the embedded tactile sensors. The studied online model achieves a localization error of $5.7 \pm 3.0$ mm. This research contributes a versatile tool and robust solution for contact localization that is ambiguous in shape and internal sensor distribution.

This paper presents a novel manipulation strategy that uses keypoint correspondences extracted from visuo-tactile sensor images to facilitate precise object manipulation. Our approach uses the visuo-tactile feedback to guide the robot's actions for accurate object grasping and placement, eliminating the need for post-grasp adjustments and extensive training. This method provides an improvement in deployment efficiency, addressing the challenges of manipulation tasks in environments where object locations are not predefined. We validate the effectiveness of our strategy through experiments demonstrating the extraction of keypoint correspondences and their application to real-world tasks such as block alignment and gear insertion, which require millimeter-level precision. The results show an average error margin significantly lower than that of traditional vision-based methods, which is sufficient to achieve the target tasks.

We present VERF, a collection of two methods (VERF-PnP and VERF-Light) for providing runtime assurance on the correctness of a camera pose estimate of a monocular camera without relying on direct depth measurements. We leverage the ability of NeRF (Neural Radiance Fields) to render novel RGB perspectives of a scene. We only require as input the camera image whose pose is being estimated, an estimate of the camera pose we want to monitor, and a NeRF model containing the scene pictured by the camera. We can then predict if the pose estimate is within a desired distance from the ground truth and justify our prediction with a level of confidence. VERF-Light does this by rendering a viewpoint with NeRF at the estimated pose and estimating its relative offset to the sensor image up to scale. Since scene scale is unknown, the approach renders another auxiliary image and reasons over the consistency of the optical flows across the three images. VERF-PnP takes a different approach by rendering a stereo pair of images with NeRF and utilizing the Perspective-n-Point (PnP) algorithm. We evaluate both methods on the LLFF dataset, on data from a Unitree A1 quadruped robot, and on data collected from Blue Origin's sub-orbital New Shepard rocket to demonstrate the effectiveness of the proposed pose monitoring method across a range of scene scales. We also show monitoring can be completed in under half a second on a 3090 GPU.

We present a probabilistic method for fusion of images produced by multiple sensors. The approach is based on an image formation model in which the sensor images are noisy, locally linear functions of an underlying, true scene. A Bayesian framework then provides for maximum likelihood or maximum a posteriori estimates of the true scene from the sensor images. Maximum likelihood estimates of the parameters of the image formation model involve (local) second order image statistics, and thus are related to local principal component analysis. We demonstrate the efficacy of the method on images from visible-band and infrared sensors.

Deep lens optimization has recently emerged as a new paradigm for designing computational imaging systems, however it has been limited to either simple optical systems consisting of a single DOE or metalens, or the fine-tuning of compound lenses from good initial designs. Here we present a deep lens design method based on curriculum learning, which is able to learn optical designs of compound lenses ab initio from randomly initialized surfaces, therefore overcoming the need for a good initial design. We demonstrate this approach with the fully-automatic design of an extended depth-of-field computational camera in a cellphone-style form factor, highly aspherical surfaces, and a short back focal length.

An industrial connector insertion task requires submillimeter positioning and grasp pose compensation for a plug. Thus, highly accurate estimation of the relative pose between a plug and socket is fundamental for achieving the task. World models are promising technologies for visuomotor control because they obtain appropriate state representation to jointly optimize feature extraction and latent dynamics model. Recent studies show that the NewtonianVAE, a type of the world model, acquires latent space equivalent to mapping from images to physical coordinates. Proportional control can be achieved in the latent space of NewtonianVAE. However, applying NewtonianVAE to high-accuracy industrial tasks in physical environments is an open problem. Moreover, the existing framework does not consider the grasp pose compensation in the obtained latent space. In this work, we proposed tactile-sensitive NewtonianVAE and applied it to a USB connector insertion with grasp pose variation in the physical environments. We adopted a GelSight-type tactile sensor and estimated the insertion position compensated by the grasp pose of the plug. Our method trains the latent space in an end-to-end manner, and no additional engineering and annotation are required. Simple proportional control is available in the obtained latent space. Moreover, we showed that the original NewtonianVAE fails in some situations, and demonstrated that domain knowledge induction improves model accuracy. This domain knowledge can be easily obtained using robot specification and grasp pose error measurement. We demonstrated that our proposed method achieved a 100\% success rate and 0.3 mm positioning accuracy in the USB connector insertion task in the physical environment. It outperformed SOTA CNN-based two-stage goal pose regression with grasp pose compensation using coordinate transformation.

We present a probabilistic method for fusion of images produced by multiple sensors. The approach is based on an image formation model in which the sensor images are noisy, locally linear functions of an underlying, true scene. A Bayesian framework then provides for maximum likelihood or maximum a posteriori estimates of the true scene from the sensor images. Maximum likelihood estimates of the parameters of the image formation model involve (local) second order image statistics, and thus are related to local principal component analysis. We demonstrate the efficacy of the method on images from visible-band and infrared sensors. 1 Introduction Advances in sensing devices have fueled the deployment of multiple sensors in several computational vision systems [1, for example]. Using multiple sensors can increase reliability with respect to single sensor systems.

We present a probabilistic method for fusion of images produced by multiple sensors. The approach is based on an image formation model in which the sensor images are noisy, locally linear functions of an underlying, true scene. A Bayesian framework then provides for maximum likelihood or maximum a posteriori estimates of the true scene from the sensor images. Maximum likelihood estimates of the parameters of the image formation model involve (local) second order image statistics, and thus are related to local principal component analysis. We demonstrate the efficacy of the method on images from visible-band and infrared sensors. 1 Introduction Advances in sensing devices have fueled the deployment of multiple sensors in several computational vision systems [1, for example]. Using multiple sensors can increase reliability with respect to single sensor systems.