ترغب بنشر مسار تعليمي؟ اضغط هنا

Uncertainty-Aware Reinforcement Learning for Collision Avoidance

264   0   0.0 ( 0 )
 نشر من قبل Gregory Kahn
 تاريخ النشر 2017
  مجال البحث الهندسة المعلوماتية
والبحث باللغة English




اسأل ChatGPT حول البحث

Reinforcement learning can enable complex, adaptive behavior to be learned automatically for autonomous robotic platforms. However, practical deployment of reinforcement learning methods must contend with the fact that the training process itself can be unsafe for the robot. In this paper, we consider the specific case of a mobile robot learning to navigate an a priori unknown environment while avoiding collisions. In order to learn collision avoidance, the robot must experience collisions at training time. However, high-speed collisions, even at training time, could damage the robot. A successful learning method must therefore proceed cautiously, experiencing only low-speed collisions until it gains confidence. To this end, we present an uncertainty-aware model-based learning algorithm that estimates the probability of collision together with a statistical estimate of uncertainty. By formulating an uncertainty-dependent cost function, we show that the algorithm naturally chooses to proceed cautiously in unfamiliar environments, and increases the velocity of the robot in settings where it has high confidence. Our predictive model is based on bootstrapped neural networks using dropout, allowing it to process raw sensory inputs from high-bandwidth sensors such as cameras. Our experimental evaluation demonstrates that our method effectively minimizes dangerous collisions at training time in an obstacle avoidance task for a simulated and real-world quadrotor, and a real-world RC car. Videos of the experiments can be found at https://sites.google.com/site/probcoll.



قيم البحث

اقرأ أيضاً

Exploration in reinforcement learning is a challenging problem: in the worst case, the agent must search for high-reward states that could be hidden anywhere in the state space. Can we define a more tractable class of RL problems, where the agent is provided with examples of successful outcomes? In this problem setting, the reward function can be obtained automatically by training a classifier to categorize states as successful or not. If trained properly, such a classifier can provide a well-shaped objective landscape that both promotes progress toward good states and provides a calibrated exploration bonus. In this work, we show that an uncertainty aware classifier can solve challenging reinforcement learning problems by both encouraging exploration and provided directed guidance towards positive outcomes. We propose a novel mechanism for obtaining these calibrated, uncertainty-aware classifiers based on an amortized technique for computing the normalized maximum likelihood (NML) distribution. To make this tractable, we propose a novel method for computing the NML distribution by using meta-learning. We show that the resulting algorithm has a number of intriguing connections to both count-based exploration methods and prior algorithms for learning reward functions, while also providing more effective guidance towards the goal. We demonstrate that our algorithm solves a number of challenging navigation and robotic manipulation tasks which prove difficult or impossible for prior methods.
It is challenging for a mobile robot to navigate through human crowds. Existing approaches usually assume that pedestrians follow a predefined collision avoidance strategy, like social force model (SFM) or optimal reciprocal collision avoidance (ORCA ). However, their performances commonly need to be further improved for practical applications, where pedestrians follow multiple different collision avoidance strategies. In this paper, we propose a map-based deep reinforcement learning approach for crowd-aware robot navigation with various pedestrians. We use the sensor map to represent the environmental information around the robot, including its shape and observable appearances of obstacles. We also introduce the pedestrian map that specifies the movements of pedestrians around the robot. By applying both maps as inputs of the neural network, we show that a navigation policy can be trained to better interact with pedestrians following different collision avoidance strategies. We evaluate our approach under multiple scenarios both in the simulator and on an actual robot. The results show that our approach allows the robot to successfully interact with various pedestrians and outperforms compared methods in terms of the success rate.
The focus of this work is to present a novel methodology for optimal distribution of a swarm formation on either side of an obstacle, when evading the obstacle, to avoid overpopulation on the sides to reduce the agents waiting delays, resulting in a reduced overall mission time and lower energy consumption. To handle this, the problem is divided into two main parts: 1) the disturbance phase: how to morph the formation optimally to avoid the obstacle in the least possible time in the situation at hand, and 2) the convergence phase: how to optimally resume the intended formation shape once the threat of potential collision has been eliminated. For the first problem, we develop a methodology which tests different formation morphing combinations and finds the optimal one, by utilizing trajectory, velocity, and coordinate information, to bypass the obstacle. For the second problem, we utilize a thin-plate splines (TPS) inspired temperature function minimization method to bring the agents back from the distorted formation into the desired formation in an optimal manner, after collision avoidance has been successfully performed. Experimental results show that, in the considered test scenario, the traditional method based on the shortest path results in 14.7% higher energy consumption as compared to our proposed approach.
With the rapid development of autonomous driving, collision avoidance has attracted attention from both academia and industry. Many collision avoidance strategies have emerged in recent years, but the dynamic and complex nature of driving environment poses a challenge to develop robust collision avoidance algorithms. Therefore, in this paper, we propose a decentralized framework named RACE: Reinforced Cooperative Autonomous Vehicle Collision AvoidancE. Leveraging a hierarchical architecture we develop an algorithm named Co-DDPG to efficiently train autonomous vehicles. Through a security abiding channel, the autonomous vehicles distribute their driving policies. We use the relative distances obtained by the opponent sensors to build the VANET instead of locations, which ensures the vehicles location privacy. With a leader-follower architecture and parameter distribution, RACE accelerates the learning of optimal policies and efficiently utilizes the remaining resources. We implement the RACE framework in the widely used TORCS simulator and conduct various experiments to measure the performance of RACE. Evaluations show that RACE quickly learns optimal driving policies and effectively avoids collisions. Moreover, RACE also scales smoothly with varying number of participating vehicles. We further compared RACE with existing autonomous driving systems and show that RACE outperforms them by experiencing 65% less collisions in the training process and exhibits improved performance under varying vehicle density.
123 - Xu Xie , Chi Zhang , Yixin Zhu 2021
Predicting agents future trajectories plays a crucial role in modern AI systems, yet it is challenging due to intricate interactions exhibited in multi-agent systems, especially when it comes to collision avoidance. To address this challenge, we prop ose to learn congestion patterns as contextual cues explicitly and devise a novel Sense--Learn--Reason--Predict framework by exploiting advantages of three different doctrines of thought, which yields the following desirable benefits: (i) Representing congestion as contextual cues via latent factors subsumes the concept of social force commonly used in physics-based approaches and implicitly encodes the distance as a cost, similar to the way a planning-based method models the environment. (ii) By decomposing the learning phases into two stages, a student can learn contextual cues from a teacher while generating collision-free trajectories. To make the framework computationally tractable, we formulate it as an optimization problem and derive an upper bound by leveraging the variational parametrization. In experiments, we demonstrate that the proposed model is able to generate collision-free trajectory predictions in a synthetic dataset designed for collision avoidance evaluation and remains competitive on the commonly used NGSIM US-101 highway dataset.

الأسئلة المقترحة

التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا