arXiv subjects

Tim Welschehold

Publications and source records attributed to Tim Welschehold.

30 records · Page 2Linked to original sources

arXiv2023

Dynamic Update-to-Data Ratio: Minimizing World Model Overfitting

Early stopping based on the validation set performance is a popular approach to find the right balance between under- and overfitting in the context of supervised learning. However, in reinforcement learning, even for supervised sub-problems such as world model learning, early stopping is not applicable as the dataset is continually evolving. As a solution, we propose a new general method that dynamically adjusts the update to data (UTD) ratio during training based on under- and overfitting detection on a small subset of the continuously collected experience not used for training. We apply our method to DreamerV2, a state-of-the-art model-based reinforcement learning algorithm, and evaluate it on the DeepMind Control Suite and the Atari $100$k benchmark. The results demonstrate that one can better balance under- and overestimation by adjusting the UTD ratio with our approach compared to the default setting in DreamerV2 and that it is competitive with an extensive hyperparameter search which is not feasible for many applications. Our method eliminates the need to set the UTD hyperparameter by hand and even leads to a higher robustness with regard to other learning-related hyperparameters further reducing the amount of necessary tuning.

cs.LG↗

arXiv2023

Catch Me If You Hear Me: Audio-Visual Navigation in Complex Unmapped Environments with Moving Sounds

Audio-visual navigation combines sight and hearing to navigate to a sound-emitting source in an unmapped environment. While recent approaches have demonstrated the benefits of audio input to detect and find the goal, they focus on clean and static sound sources and struggle to generalize to unheard sounds. In this work, we propose the novel dynamic audio-visual navigation benchmark which requires catching a moving sound source in an environment with noisy and distracting sounds, posing a range of new challenges. We introduce a reinforcement learning approach that learns a robust navigation policy for these complex settings. To achieve this, we propose an architecture that fuses audio-visual information in the spatial feature space to learn correlations of geometric information inherent in both local maps and audio signals. We demonstrate that our approach consistently outperforms the current state-of-the-art by a large margin across all tasks of moving sounds, unheard sounds, and noisy environments, on two challenging 3D scanned real-world environments, namely Matterport3D and Replica. The benchmark is available at http://dav-nav.cs.uni-freiburg.de.

cs.SD↗

arXiv2022

Adaptively Calibrated Critic Estimates for Deep Reinforcement Learning

Accurate value estimates are important for off-policy reinforcement learning. Algorithms based on temporal difference learning typically are prone to an over- or underestimation bias building up over time. In this paper, we propose a general method called Adaptively Calibrated Critics (ACC) that uses the most recent high variance but unbiased on-policy rollouts to alleviate the bias of the low variance temporal difference targets. We apply ACC to Truncated Quantile Critics, which is an algorithm for continuous control that allows regulation of the bias with a hyperparameter tuned per environment. The resulting algorithm adaptively adjusts the parameter during training rendering hyperparameter search unnecessary and sets a new state of the art on the OpenAI gym continuous control benchmark among all algorithms that do not tune hyperparameters for each environment. ACC further achieves improved results on different tasks from the Meta-World robot benchmark. Additionally, we demonstrate the generality of ACC by applying it to TD3 and showing an improved performance also in this setting.

cs.LG↗

arXiv2022

Self-Supervised Learning of Multi-Object Keypoints for Robotic Manipulation

In recent years, policy learning methods using either reinforcement or imitation have made significant progress. However, both techniques still suffer from being computationally expensive and requiring large amounts of training data. This problem is especially prevalent in real-world robotic manipulation tasks, where access to ground truth scene features is not available and policies are instead learned from raw camera observations. In this paper, we demonstrate the efficacy of learning image keypoints via the Dense Correspondence pretext task for downstream policy learning. Extending prior work to challenging multi-object scenes, we show that our model can be trained to deal with important problems in representation learning, primarily scale-invariance and occlusion. We evaluate our approach on diverse robot manipulation tasks, compare it to other visual representation learning approaches, and demonstrate its flexibility and effectiveness for sample-efficient policy learning.

cs.RO↗

arXiv2022

Robot Skill Adaptation via Soft Actor-Critic Gaussian Mixture Models

A core challenge for an autonomous agent acting in the real world is to adapt its repertoire of skills to cope with its noisy perception and dynamics. To scale learning of skills to long-horizon tasks, robots should be able to learn and later refine their skills in a structured manner through trajectories rather than making instantaneous decisions individually at each time step. To this end, we propose the Soft Actor-Critic Gaussian Mixture Model (SAC-GMM), a novel hybrid approach that learns robot skills through a dynamical system and adapts the learned skills in their own trajectory distribution space through interactions with the environment. Our approach combines classical robotics techniques of learning from demonstration with the deep reinforcement learning framework and exploits their complementary nature. We show that our method utilizes sensors solely available during the execution of preliminarily learned skills to extract relevant features that lead to faster skill refinement. Extensive evaluations in both simulation and real-world environments demonstrate the effectiveness of our method in refining robot skills by leveraging physical interactions, high-dimensional sensory data, and sparse task completion rewards. Videos, code, and pre-trained models are available at http://sac-gmm.cs.uni-freiburg.de.

cs.RO↗

arXiv2022

Learning Long-Horizon Robot Exploration Strategies for Multi-Object Search in Continuous Action Spaces

Recent advances in vision-based navigation and exploration have shown impressive capabilities in photorealistic indoor environments. However, these methods still struggle with long-horizon tasks and require large amounts of data to generalize to unseen environments. In this work, we present a novel reinforcement learning approach for multi-object search that combines short-term and long-term reasoning in a single model while avoiding the complexities arising from hierarchical structures. In contrast to existing multi-object search methods that act in granular discrete action spaces, our approach achieves exceptional performance in continuous action spaces. We perform extensive experiments and show that it generalizes to unseen apartment environments with limited data. Furthermore, we demonstrate zero-shot transfer of the learned policies to an office environment in real world experiments.

cs.RO↗

arXiv2022

Doing Right by Not Doing Wrong in Human-Robot Collaboration

As robotic systems become more and more capable of assisting humans in their everyday lives, we must consider the opportunities for these artificial agents to make their human collaborators feel unsafe or to treat them unfairly. Robots can exhibit antisocial behavior causing physical harm to people or reproduce unfair behavior replicating and even amplifying historical and societal biases which are detrimental to humans they interact with. In this paper, we discuss these issues considering sociable robotic manipulation and fair robotic decision making. We propose a novel approach to learning fair and sociable behavior, not by reproducing positive behavior, but rather by avoiding negative behavior. In this study, we highlight the importance of incorporating sociability in robot manipulation, as well as the need to consider fairness in human-robot interactions.

cs.RO↗

arXiv2022

Correct Me if I am Wrong: Interactive Learning for Robotic Manipulation

Learning to solve complex manipulation tasks from visual observations is a dominant challenge for real-world robot learning. Although deep reinforcement learning algorithms have recently demonstrated impressive results in this context, they still require an impractical amount of time-consuming trial-and-error iterations. In this work, we consider the promising alternative paradigm of interactive learning in which a human teacher provides feedback to the policy during execution, as opposed to imitation learning where a pre-collected dataset of perfect demonstrations is used. Our proposed CEILing (Corrective and Evaluative Interactive Learning) framework combines both corrective and evaluative feedback from the teacher to train a stochastic policy in an asynchronous manner, and employs a dedicated mechanism to trade off human corrections with the robot's own experience. We present results obtained with our framework in extensive simulation and real-world experiments to demonstrate that CEILing can effectively solve complex robot manipulation tasks directly from raw images in less than one hour of real-world training.

cs.RO↗

arXiv2021

Learning Kinematic Feasibility for Mobile Manipulation through Deep Reinforcement Learning

Mobile manipulation tasks remain one of the critical challenges for the widespread adoption of autonomous robots in both service and industrial scenarios. While planning approaches are good at generating feasible whole-body robot trajectories, they struggle with dynamic environments as well as the incorporation of constraints given by the task and the environment. On the other hand, dynamic motion models in the action space struggle with generating kinematically feasible trajectories for mobile manipulation actions. We propose a deep reinforcement learning approach to learn feasible dynamic motions for a mobile base while the end-effector follows a trajectory in task space generated by an arbitrary system to fulfill the task at hand. This modular formulation has several benefits: it enables us to readily transform a broad range of end-effector motions into mobile applications, it allows us to use the kinematic feasibility of the end-effector trajectory as a dense reward signal and its modular formulation allows it to generalise to unseen end-effector motions at test time. We demonstrate the capabilities of our approach on multiple mobile robot platforms with different kinematic abilities and different types of wheeled platforms in extensive simulated as well as real-world experiments.

cs.RO↗

arXiv2021

Courteous Behavior of Automated Vehicles at Unsignalized Intersections via Reinforcement Learning

The transition from today's mostly human-driven traffic to a purely automated one will be a gradual evolution, with the effect that we will likely experience mixed traffic in the near future. Connected and automated vehicles can benefit human-driven ones and the whole traffic system in different ways, for example by improving collision avoidance and reducing traffic waves. Many studies have been carried out to improve intersection management, a significant bottleneck in traffic, with intelligent traffic signals or exclusively automated vehicles. However, the problem of how to improve mixed traffic at unsignalized intersections has received less attention. In this paper, we propose a novel approach to optimizing traffic flow at intersections in mixed traffic situations using deep reinforcement learning. Our reinforcement learning agent learns a policy for a centralized controller to let connected autonomous vehicles at unsignalized intersections give up their right of way and yield to other vehicles to optimize traffic flow. We implemented our approach and tested it in the traffic simulator SUMO based on simulated and real traffic data. The experimental evaluation demonstrates that our method significantly improves traffic flow through unsignalized intersections in mixed traffic settings and also provides better performance on a wide range of traffic situations compared to the state-of-the-art traffic signal controller for the corresponding signalized intersection.

cs.LG↗

arXiv2019

Combined Task and Action Learning from Human Demonstrations for Mobile Manipulation Applications

Learning from demonstrations is a promising paradigm for transferring knowledge to robots. However, learning mobile manipulation tasks directly from a human teacher is a complex problem as it requires learning models of both the overall task goal and of the underlying actions. Additionally, learning from a small number of demonstrations often introduces ambiguity with respect to the intention of the teacher, making it challenging to commit to one model for generalizing the task to new settings. In this paper, we present an approach to learning flexible mobile manipulation action models and task goal representations from teacher demonstrations. Our action models enable the robot to consider different likely outcomes of each action and to generate feasible trajectories for achieving them. Accordingly, we leverage a probabilistic framework based on Monte Carlo tree search to compute sequences of feasible actions imitating the teacher intention in new settings without requiring the teacher to specify an explicit goal state. We demonstrate the effectiveness of our approach in complex tasks carried out in real-world settings.

cs.RO↗

arXiv2018

3D Human Pose Estimation in RGBD Images for Robotic Task Learning

We propose an approach to estimate 3D human pose in real world units from a single RGBD image and show that it exceeds performance of monocular 3D pose estimation approaches from color as well as pose estimation exclusively from depth. Our approach builds on robust human keypoint detectors for color images and incorporates depth for lifting into 3D. We combine the system with our learning from demonstration framework to instruct a service robot without the need of markers. Experiments in real world settings demonstrate that our approach enables a PR2 robot to imitate manipulation actions observed from a human teacher.

cs.CV↗