Related papers: Sym2Real: Symbolic Dynamics with Residual Learning…

The engineering community currently encounters significant challenges in the development of intelligent transportation algorithms that can be transferred from simulation to reality with minimal effort. This can be achieved by robustifying…

Many real-world safety-critical systems are governed by explicit rules that define unsafe world configurations and constrain agent interactions. In practice, these rules are complex and context-dependent, making manual specification…

Obstacle avoidance is a fundamental vision-based task essential for enabling quadrotors to perform advanced applications. When planning the trajectory, existing approaches both on optimization and learning typically regard quadrotor as a…

Sim-to-real transfer remains a significant challenge in robotics due to the discrepancies between simulated and real-world dynamics. Traditional methods like Domain Randomization often fail to capture fine-grained dynamics, limiting their…

One of the most critical aspects of multimodal Reinforcement Learning (RL) is the effective integration of different observation modalities. Having robust and accurate representations derived from these modalities is key to enhancing the…

This paper presents an empirical study of reset-free reinforcement learning (RL) for real-world agile driving, in which a physical 1/10-scale vehicle learns continuously on a slippery indoor track without manual resets. High-speed driving…

We consider joint trajectory generation and tracking control for under-actuated robotic systems. A common solution is to use a layered control architecture, where the top layer uses a simplified model of system dynamics for trajectory…

Real-world physics can only be analytically modeled with a certain level of precision for modern intricate robotic systems. As a result, tracking aggressive trajectories accurately could be challenging due to the existence of residual…

Virtual testing is a crucial task to ensure safety in autonomous driving, and sensor simulation is an important task in this domain. Most current LiDAR simulations are very simplistic and are mainly used to perform initial tests, while the…

Advanced vehicle control is a fundamental building block in the development of autonomous driving systems. Reinforcement learning (RL) promises to achieve control performance superior to classical approaches while keeping computational…

Robotic manipulation of slender objects is challenging, especially when the induced deformations are large and nonlinear. Traditionally, learning-based control approaches, such as imitation learning, have been used to address deformable…

Whereas reinforcement learning has been applied with success to a range of robotic control problems in complex, uncertain environments, reliance on extensive data - typically sourced from simulation environments - limits real-world…

To achieve fully autonomous driving, vehicles must be capable of continuously performing various driving tasks, including lane keeping and car following, both of which are fundamental and well-studied driving ones. However, previous studies…

A majority of microrobots are constructed using compliant materials that are difficult to model analytically, limiting the utility of traditional model-based controllers. Challenges in data collection on microrobots and large errors between…

Recently, learning-based controllers have been shown to push mobile robotic systems to their limits and provide the robustness needed for many real-world applications. However, only classical optimization-based control frameworks offer the…

We study sim-to-real skill transfer and discovery in the context of robotics control using representation learning. We draw inspiration from spectral decomposition of Markov decision processes. The spectral decomposition brings about…

Reinforcement learning encounters many challenges when applied directly in the real world. Sim-to-real transfer is widely used to transfer the knowledge learned from simulation to the real world. Domain randomization -- one of the most…

The manual design of soft robots and their controllers is notoriously challenging, but it could be augmented---or, in some cases, entirely replaced---by automated design tools. Machine learning algorithms can automatically propose, test,…

High-fidelity and controllable 3D simulation is essential for addressing the long-tail data scarcity in Autonomous Driving (AD), yet existing methods struggle to simultaneously achieve photorealistic rendering and interactive traffic…

Generating large-scale synthetic data in simulation is a feasible alternative to collecting/labelling real data for training vision-based deep learning models, albeit the modelling inaccuracies do not generalize to the physical world. In…