Collision avoidance for mobile robots with limited sensing and limited information about moving obstacles

Phan, Dung; Yang, Junxing; Grosu, Radu; Smolka, Scott A.; Stoller, Scott D.

doi:10.1007/s10703-016-0265-4

Cited by 19 publications

(13 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both dynamic window algorithm (DWA) [18] and ant colony optimization (ACO) [19] can be applied to robot path planning in dynamic complex environment. As classical path planning algorithms, these two algorithms also have good performance.…”

Section: Comparison With Other Methodsmentioning

confidence: 99%

Path planning of mobile robot in dynamic environment: fuzzy artificial potential field and extensible neural network

Wang

Chen

Zhang

et al. 2020

Artif Life Robotics

View full text Add to dashboard Cite

Path planning in dynamic environment is a great challenge for mobile robot. A large number of approaches have been used to deal with it. Since the neural network algorithm has the ability to find the optimal solution at high speed and self-learning function, it has achieved extensive applications in the path planning tasks. Considering that the optimization performance of the neural network heavily depends on the quality of the training sample, this paper proposes a novel way to provide the training samples for the neural network. Work space of the robot is divided into two parts: global safe area and local dangerous area. In the global safe area, the robot only receives the attraction force from the target and it moves towards the target directly. In the dangerous area, except the attraction force, the robot also receives the repulsion force from the obstacle(s). The repulsion force and the angle between the obstacle and the target (origin of the coordinate is in the position of the robot) are used to be the inputs of the fuzzy inferencing system, and the deflection angle of the robot is the output. The final moving direction of the robot is determined by summing this deflection angle and the direction of the attraction force. The coordinates of the target and obstacle, and the moving direction of the robot corresponding to this position relationship, constitute the training samples for the neural network. Benefited from the precise moving direction obtained by the fuzzy artificial potential field algorithm, the neural network gets excellent path optimization ability. Simulation and physical experiment results demonstrate the potential of the proposed algorithm.

show abstract

Section: Comparison With Other Methodsmentioning

confidence: 99%

Path planning of mobile robot in dynamic environment: fuzzy artificial potential field and extensible neural network

Wang

Chen

Zhang

et al. 2020

Artif Life Robotics

View full text Add to dashboard Cite

show abstract

“…The predicted occupancy sets can also be weighted by probabilities [71], [72] d) Occlusion: The risk from occlusions is tackled either by shrinking the field of view over the prediction horizon [73]- [76] or by introducing and predicting individual, potentially present obstacles (aka phantom or virtual objects) [1], [16], [77]- [85]. Early works considering occlusions are motion planners for mobile robots [86], [73]- [75]. Later, risk assessment systems for road vehicles have included occluded intersections [77]- [80].…”

Section: A Related Workmentioning

confidence: 99%

Set-Based Prediction of Traffic Participants Considering Occlusions and Traffic Rules

Koschi

Althoff

2021

IEEE Trans. Intell. Veh.

View full text Add to dashboard Cite

Provably safe motion planning for automated road vehicles must ensure that planned motions do not result in a collision with other traffic participants. This is a major challenge in autonomous driving, since the future behavior of other traffic participants is not known and since traffic participants are often hidden due to occlusions. In this work, we propose a formal setbased prediction that contains all acceptable future behaviors of both detected and potentially hidden traffic participants. Based on formalized traffic rules and nondeterministic motion models, we perform reachability analysis to predict the set of possible occupancies and velocities of vehicles, pedestrians, and cyclists. Real-world experiments with a test vehicle in various traffic situations demonstrate the applicability and real-time capability of our over-approximative prediction for both online verification and fail-safe trajectory planning. Even in congested, complex traffic scenarios, our forecasting approach enables self-driving vehicles to never cause accidents.

show abstract

“…Override rules, sometimes also referred to as shields, have been applied ad-hoc in multiple DNN-enabled systems, such as DeepRM (Mao et al, 2016a) and Pensieve (Mao et al, 2017). Such rules, and related forms of runtime monitors, are also found in control systems for robots (Phan et al, 2017), drones (Desai et al, 2018), and in various other formalisms which are not directed particularly at deep learning (Hamlen et al, 2006;Falcone et al, 2011;Schierman et al, 2015;Ji and Lafortune, 2017;Wu et al, 2018). The formal methods community has recently taken an interest in override rules for systems with DNNs: for example, by proposing techniques to synthesize rules that affect the controller as little as possible (Avni et al, 2019;Wu et al, 2019).…”

Section: Related Workmentioning

confidence: 99%

Guarded Deep Learning using Scenario-based Modeling

Katz

2020

Proceedings of the 8th International Conference on Model-Driven Engineering and Software Development

View full text Add to dashboard Cite

Deep neural networks (DNNs) are becoming prevalent, often outperforming manually-created systems. Unfortunately, DNN models are opaque to humans, and may behave in unexpected ways when deployed. One approach for allowing safer deployment of DNN models calls for augmenting them with hand-crafted override rules, which serve to override decisions made by the DNN model when certain criteria are met. Here, we propose to bring together DNNs and the well-studied scenario-based modeling paradigm, by expressing these override rules as simple and intuitive scenarios. This approach can lead to override rules that are comprehensible to humans, but are also sufficiently expressive and powerful to increase the overall safety of the model. We describe how to extend and apply scenario-based modeling to this new setting, and demonstrate our proposed technique on multiple DNN models.

show abstract

Collision avoidance for mobile robots with limited sensing and limited information about moving obstacles

Cited by 19 publications

References 15 publications

Path planning of mobile robot in dynamic environment: fuzzy artificial potential field and extensible neural network

Path planning of mobile robot in dynamic environment: fuzzy artificial potential field and extensible neural network

Set-Based Prediction of Traffic Participants Considering Occlusions and Traffic Rules

Guarded Deep Learning using Scenario-based Modeling

Contact Info

Product

Resources

About