Disassembly is a critical challenge in maintenance and service tasks, particularly in high-precision operations such as electric vehicle (EV) battery recycling. Tasks like prying-open sealed battery covers require precise manipulation and controlled force application. In our approach we collect human demonstrations using a motion capture system, enabling the robot to learn from human-expert disassembly strategies. These demonstrations train a bimanual robotic system in which one arm exerts force with a specialized tool while the other manipulates and removes sealed components. Our method builds on a diffusion-based policy and integrates real-time force sensing to adapt its actions as contact conditions change. We decompose the demonstrations into distinct sub-tasks and apply data augmentation, thereby reducing the number of demonstrations needed and mitigating potential task failures. Our results show that the proposed method, even with a small dataset, achieves a high task success rate and efficiency compared to a standard diffusion technique. We demonstrate in a real-world application that the bimanual system effectively executes chiseling and peeling actions to separate bonded sheet from a substrate.

These days, deep learning has gained popularity as a widely used technique for image inpainting. It has the ability to not only recover the texture of a picture and extract abstract information at a high level but also restore semantic representations like human faces. Out of these methods, the use of generative adversarial networks (GANs) with autoencoder as the generator has emerged as a potential paradigm for inpainting. These models utilize the end-to-end inpainting technique to produce visually coherent and distinct image structures and textures. Nevertheless, Generative Adversarial Networks (GANs) frequently encounter issues such as gradient vanishing and model collapse when being trained. To address these challenges, we introduce a novel approach called attribute-driven training of GAN and utilize it for face image inpainting. The proposed work utilizes attributes to stabilize the training process of the generator network. It employs different training keys as training objectives to update the generator network’s parameters. Additionally, it uses a classification module, which helps determine the bestfit key. The discriminator is aided by the loss functions to critique the generated image. Experiments conducted on CelebA [25] datasets demonstrate that the proposed work effectively addresses the issue of artifacts, accomplishes consistent and efficient training, and produces visually plausible images.

Suction cups are popular for picking and transporting packages in warehouse applications. To maximize throughput, high transport speeds are desired. Many packages are deformable and may detach from the suction cups due to inertial loading if trajectories use excessive velocities. This paper introduces a novel methodology that analyzes package deformation through its curvature at the package-suction cup contact interface to generate a Factor-of-Safety (FOS) score for each waypoint in a given trajectory. By maintaining the FOS above a predetermined threshold, the trajectory planner is able to generate transport trajectories that are both safe and time-optimized. Experimental results show the method’s efficacy, demonstrating a 21.92% reduction in transport times compared to a conservative trajectory generation. Our FOS predictor identified trajectories that ensured safe package transport with 100% accuracy across all 627 real-world experiments.

Fingerprints serve as a primary means of individually identifying individuals. However, employing fingerprints in online mode poses a significant privacy risk, since it is susceptible to several forms of attack. It is plagued by issues related to privacy and security. In response to this, we proposed an innovative approach to convert the original fingerprint into a secure template that may be retained and utilized for authentication purposes. The new templates bear a resemblance to the original human fingerprints and ensure privacy by possessing the characteristic of non-invertibility. This study presented a method for generating highly authentic fingerprint templates that ensure the capacity to revoke and cancel the stolen fingerprint. Throughout the training and testing phase, we utilized the dataset derived from the Vikriti-ID fingerprint. The collection has 25000 distinct fingerprint samples, divided into five classes, with each class containing 5,000 samples. Throughout the testing phase, the comprehensive performance was evaluated based on the matching performance including EER and AUC.

Fingerprint recognition research faces significant challenges due to the limited availability of extensive and publicly available fingerprint databases. Existing databases lack a sufficient number of identities and fingerprint impressions, which hinders progress in areas such as Fingerprint-based access control. To address this challenge, we present Vikriti-ID, a synthetic fingerprint generator capable of generating unique fingerprints with multiple impressions. Using Vikriti-ID, we generated a large database containing 500000 unique fingerprints, each with 10 associated impressions. We then demonstrate the effectiveness of the database generated by Vikriti-ID by evaluating it for imposter-genuine score distribution and EER score. Apart from this we also trained a deep network to check the usability of data. We trained the network inspired from [13], on both Vikriti-ID generated data as well as public data. This generated data achieved an Equal Error Rate(EER) of 0.16%, AUC of 0.89%. This improvement is possible due to the limitations of existing publicly available data sets, which struggle in numbers or multiple impressions.

The safeguarding of biometric data is a crucial aspect of biometric authentication systems, and biometric template protection serves as a means to ensure the confidentiality of such information. In recent times, the utilization of random projection has surfaced as a viable technique for safeguarding biometric templates. This article delves deeper into the security of random projection-based techniques utilized for safeguarding biometric templates. The demonstration showcases that the security of biometric systems is compromised by non-invertibility attacks, as the protected template can be utilized by an attacker to accurately replicate the initial biometric template. A viable approach for executing non-invertibility attacks on systems, based on random projection is additionally furnished by us. The study conducted an experiment on two publicly accessible biometric datasets to demonstrate the vulnerability of random projection-based biometric template security methods. The proposed assault was utilized to recreate the original templates, highlighting the ease with which this could be accomplished. The results of our study emphasize the necessity for innovative methods in safeguarding biometric templates that are impervious to inversion.

Tool manipulation is a crucial skill for robots to perform intricate tasks, and learning from demonstration methods can provide an effective means for robots to learn these skills. However, the process of collecting human demonstration data can be challenging and may lead to information loss, requiring a large number of demonstrations to learn the human's policy. In this work, we propose a novel framework for collecting information-rich human demonstration data for learning complex tool manipulation skills. Our framework can accommodate data collection from multiple modalities such as speech, gesture, motion, video, and 3D depth data. Additionally, the framework actively queries the human expert to improve the information content of the data. We showcase the effectiveness of our method in collecting demonstration data for a complex granular media transport task and performing the task on a real robot.

This work proposes a novel application of digital twins in the field of biometric security. Biometric systems have become widespread but their use carries risks of privacy invasion attacks due to the sensitive nature of biometric data. To address these concerns, we propose creating biometric clones for digital access and authentication systems. A user's fingerprint can act as a virtual representation or cyberproxy, allowing users to exist in the digital world with a unique, changeable, and privacy-preserving identity. The digital twin or clone fingerprint is generated using deep neural networks combined with a user-specific token/key. This approach allows third parties to process and store the proxy biometrics without putting the user's personal information at risk. We suggest that this approach could provide a safer and more secure alternative to traditional biometric security systems.