ETH Zurich

About: ETH Zurich is a education organization based out in Zurich, Switzerland. It is known for research contribution in the topics: Population & Computer science. The organization has 48393 authors who have published 122408 publications receiving 5111383 citations. The organization is also known as: Swiss Federal Institute of Technology in Zurich & Eidgenössische Technische Hochschule Zürich.

Depth and Appearance for Mobile Scene Analysis

Abstract: In this paper, we address the challenging problem of simultaneous pedestrian detection and ground-plane estimation from video while walking through a busy pedestrian zone. Our proposed system integrates robust stereo depth cues, ground-plane estimation, and appearance-based object detection in a principled fashion using a graphical model. Object-object occlusions lead to complex interactions in this model that make an exact solution computationally intractable. We therefore propose a novel iterative approach that first infers scene geometry using belief propagation and then resolves interactions between objects using a global optimization procedure. This approach leads to a robust solution in few iterations, while allowing object detection to benefit from geometry estimation and vice versa. We quantitatively evaluate the performance of our proposed approach on several challenging test sequences showing strolls through busy shopping streets. Comparisons to various baseline systems show that it outperforms both a system using no scene geometry and one just relying on structure-from-motion without dense stereo.

Compactness results in Symplectic Field Theory

Abstract: This is one in a series of papers devoted to the foundations of Symplectic Field Theory sketched in (4). We prove compactness results for moduli spaces of holomorphic curves arising in Symplectic Field Theory. The theorems generalize Gromov's compactness theorem in (8) as well as compactness theorems in Floer homology theory, (6, 7), and in contact geometry, (9, 19).

Learning quadrupedal locomotion over challenging terrain

Abstract: Legged locomotion can extend the operational domain of robots to some of the most challenging environments on Earth. However, conventional controllers for legged locomotion are based on elaborate state machines that explicitly trigger the execution of motion primitives and reflexes. These designs have increased in complexity but fallen short of the generality and robustness of animal locomotion. Here, we present a robust controller for blind quadrupedal locomotion in challenging natural environments. Our approach incorporates proprioceptive feedback in locomotion control and demonstrates zero-shot generalization from simulation to natural environments. The controller is trained by reinforcement learning in simulation. The controller is driven by a neural network policy that acts on a stream of proprioceptive signals. The controller retains its robustness under conditions that were never encountered during training: deformable terrains such as mud and snow, dynamic footholds such as rubble, and overground impediments such as thick vegetation and gushing water. The presented work indicates that robust locomotion in natural environments can be achieved by training in simple domains.

Are superhydrophobic surfaces best for icephobicity

Abstract: Ice formation can have catastrophic consequences for human activity on the ground and in the air. Here we investigate water freezing delays on untreated and coated surfaces ranging from hydrophilic to superhydrophobic and use these delays to evaluate icephobicity. Supercooled water microdroplets are inkjet-deposited and coalesce until spontaneous freezing of the accumulated mass occurs. Surfaces with nanometer-scale roughness and higher wettability display unexpectedly long freezing delays, at least 1 order of magnitude longer than typical superhydrophobic surfaces with larger hierarchical roughness and low wettability. Directly related to the main focus on heterogeneous nucleation and freezing delay of supercooled water droplets, the observed ensuing crystallization process consisted of two distinct phases: one very rapid recalescent partial solidification phase and a subsequent slower phase. Observations of the droplet collision process employed for the continuous liquid mass accumulation up to the poin...

Meshless deformations based on shape matching

Abstract: We present a new approach for simulating deformable objects. The underlying model is geometrically motivated. It handles pointbased objects and does not need connectivity information. The approach does not require any pre-processing, is simple to compute, and provides unconditionally stable dynamic simulations.The main idea of our deformable model is to replace energies by geometric constraints and forces by distances of current positions to goal positions. These goal positions are determined via a generalized shape matching of an undeformed rest state with the current deformed state of the point cloud. Since points are always drawn towards well-defined locations, the overshooting problem of explicit integration schemes is eliminated. The versatility of the approach in terms of object representations that can be handled, the efficiency in terms of memory and computational complexity, and the unconditional stability of the dynamic simulation make the approach particularly interesting for games.