Related papers: Predictive Red Teaming: Breaking Policies Without …

Reinforcement learning (RL) is a central problem in artificial intelligence. This problem consists of defining artificial agents that can learn optimal behaviour by interacting with an environment -- where the optimal behaviour is defined…

Execution monitor of high-level robot actions can be effectively improved by visual monitoring the state of the world in terms of preconditions and postconditions that hold before and after the execution of an action. Furthermore a policy…

End-to-end robot policies achieve high performance through neural networks trained via reinforcement learning (RL). Yet, their black box nature and abstract reasoning pose challenges for human-robot interaction (HRI), because humans may…

Robots operating alongside humans often encounter unfamiliar environments that make autonomous task completion challenging. Though improving models and increasing dataset size can enhance a robot's performance in unseen environments, data…

The subject of this paper is reinforcement learning. Policies are considered here that produce actions based on states and random elements autocorrelated in subsequent time instants. Consequently, an agent learns from experiments that are…

Prompt tuning and adapter tuning have shown great potential in transferring pre-trained vision-language models (VLMs) to various downstream tasks. In this work, we design a new type of tuning method, termed as regularized mask tuning, which…

A command-following robot that serves people in everyday life must continually improve itself in deployment domains with minimal help from its end users, instead of engineers. Previous methods are either difficult to continuously improve…

As deep neural networks(DNN) become increasingly prevalent, particularly in high-stakes areas such as autonomous driving and healthcare, the ability to detect incorrect predictions of models and intervene accordingly becomes crucial for…

Navigation in natural outdoor environments requires a robust and reliable traversability classification method to handle the plethora of situations a robot can encounter. Binary classification algorithms perform well in their native domain…

Tracking a target in cluttered and dynamic environments is challenging but forms a core component in applications like aerial cinematography. The obstacles in the environment not only pose collision risk but can also occlude the target from…

In data sequences measured over space or time, an important problem is accurate detection of abrupt changes. In partially labeled data, it is important to correctly predict presence/absence of changes in positive/negative labeled regions,…

Diffusion Policy (DP) enables robots to learn complex behaviors by imitating expert demonstrations through action diffusion. However, in practical applications, hardware limitations often degrade data quality, while real-time constraints…

As vision-language models (VLMs) gain prominence, their multimodal interfaces also introduce new safety vulnerabilities, making the safety evaluation challenging and critical. Existing red-teaming efforts are either restricted to a narrow…

As drones and autonomous cars become more widespread it is becoming increasingly important that robots can operate safely under realistic conditions. The noisy information fed into real systems means that robots must use estimates of the…

Increasing interest in integrating advanced robotics within manufacturing has spurred a renewed concentration in developing real-time scheduling solutions to coordinate human-robot collaboration in this environment. Traditionally, the…

Traversability estimation in rugged, unstructured environments remains a challenging problem in field robotics. Often, the need for precise, accurate traversability estimation is in direct opposition to the limited sensing and compute…

For reliable deployment of deep-learning systems, out-of-distribution (OOD) detection is indispensable. In the real world, where test-time inputs often arrive as streaming mixtures of in-distribution (ID) and OOD samples under evolving…

The pre-train and fine-tune paradigm in machine learning has had dramatic success in a wide range of domains because the use of existing data or pre-trained models on the internet enables quick and easy learning of new tasks. We aim to…

The use of multi-camera views simultaneously has been shown to improve the generalization capabilities and performance of visual policies. However, the hardware cost and design constraints in real-world scenarios can potentially make it…

Red teaming has proven to be an effective method for identifying and mitigating vulnerabilities in Large Language Models (LLMs). Reinforcement Fine-Tuning (RFT) has emerged as a promising strategy among existing red teaming techniques.…