相关论文: Sim2real gap is non-monotonic with robot complexit…

Tracking controllers enable robotic systems to accurately follow planned reference trajectories. In particular, reinforcement learning (RL) has shown promise in the synthesis of controllers for systems with complex dynamics and modest…

Simulation can and should play a critical role in the development and testing of algorithms for autonomous agents. What might reduce its impact is the ``sim2real'' gap -- the algorithm response differs between operation in simulated versus…

Synthetic data is being used lately for training deep neural networks in computer vision applications such as object detection, object segmentation and 6D object pose estimation. Domain randomization hereby plays an important role in…

A human-shaped robotic hand offers unparalleled versatility and fine motor skills, enabling it to perform a broad spectrum of tasks with precision, power and robustness. Across the paleontological record and animal kingdom we see a wide…

The co-design of robot morphology and neural control typically requires using reinforcement learning to approximate a unique control policy gradient for each body plan, demanding massive amounts of training data to measure the performance…

Accurate simulation of soft mechanisms under dynamic actuation is critical for the design of soft robots. We address this gap with our differentiable simulation tool by learning the material parameters of our soft robotic fish. On the…

Equipping humanoid robots with versatile interaction skills typically requires either extensive policy training or explicit human-to-robot motion retargeting. However, learning-based policies face prohibitive data collection costs.…

Simultaneously evolving morphologies (bodies) and controllers (brains) of robots can cause a mismatch between the inherited body and brain in the offspring. To mitigate this problem, the addition of an infant learning period by the…

It has been observed that the very important motion planning problem of robotics mathematically speaking boils down to the problem of finding a section to the path-space fibration, raising the notion of topological complexity, as introduced…

This article presents a new control approach and a dynamic model for engineered flapping flight with many interacting degrees of freedom. This paper explores the applications of neurobiologically inspired control systems in the form of…

Object detection in adverse weather is critical for the safety of autonomous vehicles; however, the scarcity of labelled, real-world foggy data remains a significant bottleneck. In this paper, we propose Clear2Fog (C2F), an end-to-end,…

State machine formalisms equipped with hierarchy and parallelism allow to compactly model complex system behaviours. Such models can then be transformed into executable code or inputs for model-based testing and verification techniques.…

In this study, we present a concept of morphing structure -- featuring an arch mounted on a compliant base -- that can be reconfigured via snap-through buckling and leverages bistability to retain its morphed shape. We show that…

This paper proposes a novel methodology for addressing the simulation-reality gap for multi-robot swarm systems. Rather than immediately try to shrink or `bridge the gap' anytime a real-world experiment failed that worked in simulation, we…

Flapping-wing insects, birds, and robots are thought to offset the high power cost of oscillatory wing motion by using elastic elements for energy storage and return. Insects possess highly resilient elastic regions in their flight anatomy…

Robotic cloth manipulation faces challenges due to the fabric's complex dynamics and the high dimensionality of configuration spaces. Previous methods have largely focused on isolated smoothing or folding tasks and overly reliant on…

We propose SWING: Space Walks for Implicit Network Graphs, a new class of algorithms for computations involving Graph Random Features on graphs given by implicit representations (i-graphs), where edge-weights are defined as bi-variate…

Evolving morphologies and controllers of robots simultaneously leads to a problem: Even if the parents have well-matching bodies and brains, the stochastic recombination can break this match and cause a body-brain mismatch in their…

Non-rigid 3D mesh matching is a critical step in computer vision and computer graphics pipelines. We tackle matching meshes that contain topological artefacts which can break the assumption made by current approaches. While Functional Maps…

Accurate deformable object manipulation (DOM) is essential for achieving autonomy in robotic surgery, where soft tissues are being displaced, stretched, and dissected. Many DOM methods can be powered by simulation, which ensures realistic…