相关论文: Encoding Motion Primitives for Autonomous Vehicles…

In the typical autonomous driving stack, planning and control systems represent two of the most crucial components in which data retrieved by sensors and processed by perception algorithms are used to implement a safe and comfortable…

In recent years, neural network-based image compression techniques have been able to outperform traditional codecs and have opened the gates for the development of learning-based video codecs. However, to take advantage of the high temporal…

Reinforcement learning in large-scale environments is challenging due to the many possible actions that can be taken in specific situations. We have previously developed a means of constraining, and hence speeding up, the search process…

Learning effective visuomotor policies for robots purely from data is challenging, but also appealing since a learning-based system should not require manual tuning or calibration. In the case of a robot operating in a real environment the…

Due to the challenges of processing temporal information, most trackers depend solely on visual discriminability and overlook the unique temporal coherence of video data. In this paper, we propose a lightweight and plug-and-play motion…

We present an integrated approach for perception and control for an autonomous vehicle and demonstrate this approach in a high-fidelity urban driving simulator. Our approach first builds a model for the environment, then trains a policy…

Predicting vehicle trajectories, angle and speed is important for safe and comfortable driving. We demonstrate the best predicted angle, speed, and best performance overall winning the top three places of the ICCV 2019 Learning to Drive…

This paper presents a novel neural network training approach for faster convergence and better generalization abilities in deep reinforcement learning. Particularly, we focus on the enhancement of training and evaluation performance in…

We present a control approach for autonomous vehicles based on deep reinforcement learning. A neural network agent is trained to map its estimated state to acceleration and steering commands given the objective of reaching a specific target…

The field of visual representation learning has seen explosive growth in the past years, but its benefits in robotics have been surprisingly limited so far. Prior work uses generic visual representations as a basis to learn (task-specific)…

Our work tackles the computational challenges of contrastive learning methods, particularly for the pretraining of Vision Transformers (ViTs). Despite the effectiveness of contrastive learning, the substantial computational resources…

Trajectory optimization methods have achieved an exceptional level of performance on real-world robots in recent years. These methods heavily rely on accurate analytical models of the dynamics, yet some aspects of the physical world can…

As deep neural networks are increasingly deployed in dynamic, real-world environments, relying on a single static model is often insufficient. Changes in input data distributions caused by sensor drift or lighting variations necessitate…

Neural networks are trained primarily based on their inputs and outputs, without regard for their internal mechanisms. These neglected mechanisms determine properties that are critical for safety, like (i) transparency; (ii) the absence of…

This paper develops coding techniques to reduce the running time of distributed learning tasks. It characterizes the fundamental tradeoff to compute gradients (and more generally vector summations) in terms of three parameters: computation…

Extensive literature has drawn comparisons between recordings of biological neurons in the brain and deep neural networks. This comparative analysis aims to advance and interpret deep neural networks and enhance our understanding of…

We propose a novel framework for enhancing robotic adaptability and learning efficiency, which integrates unsupervised trajectory segmentation with adaptive probabilistic movement primitives (ProMPs). By employing a cutting-edge deep…

Machine learning is evolving towards high-order models that necessitate pre-training on extensive datasets, a process associated with significant overheads. Traditional models, despite having pre-trained weights, are becoming obsolete due…

This paper proposes a novel and efficient optimization-based method for generating near time-optimal trajectories for holonomic vehicles navigating through complex but structured environments. The approach aims to solve the problem of…

Taking inspiration from how the brain coordinates multiple learning systems is an appealing strategy to endow robots with more flexibility. One of the expected advantages would be for robots to autonomously switch to the least costly system…