Related papers: Meta-Learning Online Dynamics Model Adaptation in …

Low-latency intelligent systems are required for autonomous driving on non-uniform terrain in open-pit mines and developing countries. This work proposes a perception system for autonomous vehicles on unpaved roads and off-road…

Deep learning models such as convolutional neural networks and transformers have been widely applied to solve 3D object detection problems in the domain of autonomous driving. While existing models have achieved outstanding performance on…

In autonomous navigation settings, several quantities can be subject to variations. Terrain properties such as friction coefficients may vary over time depending on the location of the robot. Also, the dynamics of the robot may change due…

We consider the problem of learning useful robotic skills from previously collected offline data without access to manually specified rewards or additional online exploration, a setting that is becoming increasingly important for scaling…

We propose a novel meta-learning framework for real-time object tracking with efficient model adaptation and channel pruning. Given an object tracker, our framework learns to fine-tune its model parameters in only a few iterations of…

We present a novel outdoor navigation algorithm to generate stable and efficient actions to navigate a robot to reach a goal. We use a multi-stage training pipeline and show that our approach produces policies that result in stable and…

A long-standing goal in AI is to develop agents capable of solving diverse tasks across a range of environments, including those never seen during training. Two dominant paradigms address this challenge: (i) reinforcement learning (RL),…

Dynamic locomotion in rough terrain requires accurate foot placement, collision avoidance, and planning of the underactuated dynamics of the system. Reliably optimizing for such motions and interactions in the presence of imperfect and…

Meta-learning algorithms can accelerate the model-based reinforcement learning (MBRL) algorithms by finding an initial set of parameters for the dynamical model such that the model can be trained to match the actual dynamics of the system…

We propose HyperDynamics, a dynamics meta-learning framework that conditions on an agent's interactions with the environment and optionally its visual observations, and generates the parameters of neural dynamics models based on inferred…

Interactive artificial intelligence in the motion control field is an interesting topic, especially when universal knowledge is adaptive to multiple tasks and universal environments. Despite there being increasing efforts in the field of…

Terrain awareness is an essential milestone to enable truly autonomous off-road navigation. Accurately predicting terrain characteristics allows optimizing a vehicle's path against potential hazards. Recent methods use deep neural networks…

Trajectory planning in autonomous driving is highly dependent on predicting the emergent behavior of other road users. Learning-based methods are currently showing impressive results in simulation-based challenges, with transformer-based…

Velocity estimation is of great importance in autonomous racing. Still, existing solutions are characterized by limited accuracy, especially in the case of aggressive driving or poor generalization to unseen road conditions. To address…

An unresolved problem in Deep Learning is the ability of neural networks to cope with domain shifts during test-time, imposed by commonly fixing network parameters after training. Our proposed method Meta Test-Time Training (MT3), however,…

We consider the problem of online control of systems with time-varying linear dynamics. This is a general formulation that is motivated by the use of local linearization in control of nonlinear dynamical systems. To state meaningful…

Real-world robots must operate under evolving dynamics caused by changing operating conditions, external disturbances, and unmodeled effects. These may appear as gradual drifts, transient fluctuations, or abrupt shifts, demanding real-time…

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…

Off-dynamics offline reinforcement learning (RL) aims to learn a policy for a target domain using limited target data and abundant source data collected under different transition dynamics. Existing methods typically address dynamics…

Model-based reinforcement learning is an effective approach for controlling an unknown system. It is based on a longstanding pipeline familiar to the control community in which one performs experiments on the environment to collect a…