Related papers: Object Goal Navigation using Data Regularized Q-Le…
Safe and real-time navigation is fundamental for humanoid robot applications. However, existing bipedal robot navigation frameworks often struggle to balance computational efficiency with the precision required for stable locomotion. We…
Semantic navigation is necessary to deploy mobile robots in uncontrolled environments like our homes, schools, and hospitals. Many learning-based approaches have been proposed in response to the lack of semantic understanding of the…
To achieve full autonomous driving, a good understanding of the surrounding environment is necessary. Especially predicting the future states of other traffic participants imposes a non-trivial challenge. Current SotA-models already show…
Navigating and understanding the real world remains a key challenge in machine learning and inspires a great variety of research in areas such as language grounding, planning, navigation and computer vision. We propose an…
Object navigation (ObjectNav) requires an agent to navigate through unseen environments to find queried objects. Many previous methods attempted to solve this task by relying on supervised or reinforcement learning, where they are trained…
Moving in dynamic pedestrian environments is one of the important requirements for autonomous mobile robots. We present a model-based reinforcement learning approach for robots to navigate through crowded environments. The navigation policy…
In this work we present a method for using Deep Q-Networks (DQNs) in multi-objective environments. Deep Q-Networks provide remarkable performance in single objective problems learning from high-level visual state representations. However,…
This work presents a modular architecture for simultaneous mapping and target driven navigation in indoors environments. The semantic and appearance stored in 2.5D map is distilled from RGB images, semantic segmentation and outputs of…
Visual navigation by mobile robots is classically tackled through SLAM plus optimal planning, and more recently through end-to-end training of policies implemented as deep networks. While the former are often limited to waypoint planning,…
We solve active target tracking, one of the essential tasks in autonomous systems, using a deep reinforcement learning (RL) approach. In this problem, an autonomous agent is tasked with acquiring information about targets of interests using…
Home-assistant robots have been a long-standing research topic, and one of the biggest challenges is searching for required objects in housing environments. Previous object-goal navigation requires the robot to search for a target object…
Learning goal conditioned control in the real world is a challenging open problem in robotics. Reinforcement learning systems have the potential to learn autonomously via trial-and-error, but in practice the costs of manual reward design,…
Many AI problems, in robotics and other domains, are goal-directed, essentially seeking a trajectory leading to some goal state. In such problems, the way we choose to represent a trajectory underlies algorithms for trajectory prediction…
Autonomous navigation in partially observable environments requires agents to reason beyond immediate sensor input, exploit occlusion, and ensure safety while progressing toward a goal. These challenges arise in many robotics domains, from…
Multi-goal policy learning for robotic manipulation is challenging. Prior successes have used state-based representations of the objects or provided demonstration data to facilitate learning. In this paper, by hand-coding a high-level…
Model-based control is a popular paradigm for robot navigation because it can leverage a known dynamics model to efficiently plan robust robot trajectories. However, it is challenging to use model-based methods in settings where the…
Reinforcement learning (RL) often struggles to accomplish a sparse-reward long-horizon task in a complex environment. Goal-conditioned reinforcement learning (GCRL) has been employed to tackle this difficult problem via a curriculum of…
We address goal-based imitation learning, where the aim is to output the symbolic goal from a third-person video demonstration. This enables the robot to plan for execution and reproduce the same goal in a completely different environment.…
This paper investigates the idea of encoding object-centered representations in the design of the reward function and policy architectures of a language-guided reinforcement learning agent. This is done using a combination of object-wise…
Vision guided navigation requires processing complex visual information to inform task-orientated decisions. Applications include autonomous robots, self-driving cars, and assistive vision for humans. A key element is the extraction and…