23 accepted papers
Existing preference optimization methods often assume scenarios where paired preference feedback (preferred/positive vs. dis-preferred/negative examples) is available. This requirement limits their applicability in scenarios where only unpaired feedback—for example, either positive or negative— is a…
The majority of language model training builds on imitation learning. It covers pretraining, supervised fine-tuning, and affects the starting conditions for reinforcement learning from human feedback (RLHF). The simplicity and scalability of maximum likelihood estimation (MLE) for next token predict…
Reinforcement learning solely from an agent’s self-generated data is often believed to be infeasible for learning on real robots, due to the amount of data needed. However, if done right, agents learning from real data can be surprisingly efficient through re-using previously collected sub-optimal d…
We show that offline actor-critic reinforcement learning can scale to large models - such as transformers - and follows similar scaling laws as supervised learning. We find that offline actor-critic algorithms can outperform strong, supervised, behavioral cloning baselines for multi-task training on…
Algorithms for self-learning systems have made considerable progress in recent years, yet safety concerns and the need for additional instrumentation have so far largely limited learning experiments with real robots to well controlled lab settings. In this paper, we demonstrate how a small bipedal r…
Generally capable Spatial AI systems must build persistent scene representations where geometric models are combined with meaningful semantic labels. The many approaches to labelling scenes can be divided into two clear groups: view-based which estimate labels from the input view-wise data and then…
Modern Reinforcement Learning (RL) algorithms promise to solve difficult motor control problems directly from raw sensory inputs. Their attraction is due in part to the fact that they can represent a general class of methods that allow to learn a solution with a reasonably set reward and minimal pri
Dense visual SLAM methods are able to estimate the 3D structure of an environment and locate the observer within them. They estimate the motion of a camera by matching visual information between consecutive frames, and are thus prone to failure under extreme motion conditions or when observing textu…
Estimating motion and surrounding geometry of a moving camera remains a challenging inference problem. From an information theoretic point of view, estimates should get better as more information is included, such as is done in dense SLAM, but this is strongly dependent on the validity of the underl…
We propose a new multi-instance dynamic RGB-D SLAM system using an object-level octree-based volumetric representation. It can provide robust camera tracking in dynamic environments and at the same time, continuously estimate geometric, semantic, and motion properties for arbitrary objects in the sc…
Systems which incrementally create 3D semantic maps from image sequences must store and update representations of both geometry and semantic entities. However, while there has been much work on the correct formulation for geometrical estimation, state-of-the-art systems usually rely on simple semant…
The representation of geometry in real-time 3D perception systems continues to be a critical research issue. Dense maps capture complete surface shape and can be augmented with semantic labels, but their high dimensionality makes them computationally costly to store and process, and unsuitable for r…
Sum-of-squares objective functions are very popular in computer vision algorithms. However, these objective functions are not always easy to optimize. The underlying assumptions made by solvers are often not satisfied and many problems are inherently ill-posed. In this paper, we propose a neural non…
Mobile robots build on accurate, real-time mapping with onboard range sensors to achieve autonomous navigation over rough terrain. Existing approaches often rely on absolute localization based on tracking of external geometric or visual features. To circumvent the reliability issues of these approac
Much like humans, robots should have the ability to leverage knowledge from previously learned tasks in order to learn new tasks quickly in new and unfamiliar environments. Despite this, most robot learning approaches have focused on learning a single task, from scratch, with a limited notion of gen
This letter deals with recursive filtering for dynamic systems where an explicit process model is not easily devisable. Most Bayesian filters assume the availability of such an explicit process model, and thus may require additional assumptions or fail to properly leverage all available information.
While dense visual SLAM methods are capable of estimating dense reconstructions of the environment, they suffer from a lack of robustness in their tracking step, especially when the optimisation is poorly initialised. Sparse visual SLAM systems have attained high levels of accuracy and robustness th…
This paper introduces ANYmal, a quadrupedal robot that features outstanding mobility and dynamic motion capability. Thanks to novel, compliant joint modules with integrated electronics, the 30 kg, 0.5 m tall robotic dog is torque controllable and very robust against impulsive loads during running or…
Flying and walking robots can use their complementary features in terms of viewpoint and payload capability to the best in a heterogeneous team. To this end, we present our online collaborative navigation framework for unknown and challenging terrain. The method leverages the flying robot's onboard…
In this paper we present a new estimation algorithm that allows for the combination of information from any number of process and measurement models. This adds more flexibility to the design of the estimator and in our case avoids the need for state augmentation. We achieve this by adapting the maxi…
Real-time dense mapping and pose estimation is essential for a wide range of navigation tasks in mobile robotic applications. We propose an odometry and mapping system that leverages the full photometric information from a stereo-vision system as well as inertial measurements in a probabilistic fram…
Quadrupedal locomotion on sloped terrains poses different challenges than walking in a mostly flat environment. The robot's configuration needs to be explicitly controlled in order to avoid slipping and kinematic limits. To this end, information about the terrain's inclination is required for carefu…
In this paper, we present a monocular visual-inertial odometry algorithm which, by directly using pixel intensity errors of image patches, achieves accurate tracking performance while exhibiting a very high level of robustness. After detection, the tracking of the multilevel patch features is closel…