32 citations · 124 across the 21 of their papers we have counts for
8 papers · 1 filter
Are Gradient-based Saliency Maps Useful in Deep Reinforcement Learning?
Matthias Rosynski, Frank Kirchner, Matias Valdenegro-Toro
Deep Reinforcement Learning (DRL) connects the classic Reinforcement Learning algorithms with Deep Neural Networks. A problem in DRL is that CNNs are black-boxes and it is hard to…
Black-Box Optimization of Object Detector Scales
Mohandass Muthuraja, Octavio Arriaga, Paul Plöger +2
Object detectors have improved considerably in the last years by using advanced CNN architectures. However, many detector hyper-parameters are generally manually tuned, or they are…
Perception for Autonomous Systems (PAZ)
Octavio Arriaga, Matias Valdenegro-Toro, Mohandass Muthuraja +2
In this paper we introduce the Perception for Autonomous Systems (PAZ) software library. PAZ is a hierarchical perception library that allow users to manipulate multiple levels of…
Learning Context-Adaptive Task Constraints for Robotic Manipulation
Dennis Mronga, Frank Kirchner
Constraint-based control approaches offer a flexible way to specify robotic manipulation tasks and execute them on robots with many degrees of freedom. However, the specification o…
Evaluating Uncertainty Estimation Methods on 3D Semantic Segmentation of Point Clouds
Swaroop Bhandary K, Nico Hochgeschwender, Paul Plöger +2
Deep learning models are extensively used in various safety critical applications. Hence these models along with being accurate need to be highly reliable. One way of achieving thi…
A Development Cycle for Automated Self-Exploration of Robot Behaviors
Thomas M. Roehr, Daniel Harnack, Hendrik Wöhrle +7
In this paper we introduce Q-Rock, a development cycle for the automated self-exploration and qualification of robot behaviors. With Q-Rock, we suggest a novel, integrative approac…
Combinatorics of a Discrete Trajectory Space for Robot Motion Planning
Felix Wiebe, Shivesh Kumar, Daniel Harnack +3
Motion planning is a difficult problem in robot control. The complexity of the problem is directly related to the dimension of the robot's configuration space. While in many theore…
Comparison of Distal Teacher Learning with Numerical and Analytical Methods to Solve Inverse Kinematics for Rigid-Body Mechanisms
Tim von Oehsen, Alexander Fabisch, Shivesh Kumar +1
Several publications are concerned with learning inverse kinematics, however, their evaluation is often limited and none of the proposed methods is of practical relevance for rigid…