Combining Onthologies and Behavior-based Control for Aware Navigation in Challenging Off-road Environments

Wolf, Patrick D.; Ropertz, Thorsten; Feldmann, Philipp; Berns, Karsten

doi:10.5220/0007934301350146

Cited by 5 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to actor hazards, environment considerations were modelled in [57] as it focused on off-road hazards. Hazards such as road type (path, path side), adverse weather and occlusion we considered.…”

Section: ) Ontology Methodsmentioning

confidence: 99%

“…As such, metrics centre around spatial and temporal features. Over half of the methods within this survey used spatial features to either semantically describe the relative location (e.g., front, behind, left, right) in the case of [18] or [18], [19], [21], [22], [35], [57], [58], [69], [70], [73], [74], [79]- [82] Temporal [19], [21], [22], [35], [69], [70], [73], [79]- [82] Behaviour [18], [19], [35], [73], [79]- [82] Spatial [18], [22], [35], [55], [56] Temporal [22], [35], [55], [56] Behaviour [18], [35] Road Type [19], [57], [58], [72] Geometry [19] Weather [18], [19],…”

Section: F Hazardous Event Quantification Metricsmentioning

confidence: 99%

“…Static Environment: To detect static hazards within the environment, [19] utilised road geometry to predict a loss of control event at sharp corners by considering curve radius, current speed and maximum deceleration. Road type can also be used to predict hazardous regions within specific domains such as intersections, which have more complex interactions, traffic density and regulation or [57] who studied hazards in offroad driving. Off-paths were also classified as more hazardous with more obstacles and uneven surfaces.…”

Section: F Hazardous Event Quantification Metricsmentioning

confidence: 99%

“…As considered in [18], who detected rain, snow and ice with more complex implementations using temperature and precipitation to predict road traction to forecast max deceleration and avoid rear-end collision in [19]. Along with creating adverse road conditions, weather conditions can also change visibility which affects vision-based sensors, and as such, methods also quantified this hazardous event by semantically classifying the range of sight (short, near, far) [70] and phenomena such as fog, snow and rain in [57] to trigger more cautious driving policy.…”

Section: F Hazardous Event Quantification Metricsmentioning

confidence: 99%

See 3 more Smart Citations

Review of Graph-Based Hazardous Event Detection Methods for Autonomous Driving Systems

Xiao

Dianati

Geiger

et al. 2023

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

show abstract

Section: ) Ontology Methodsmentioning

confidence: 99%

Section: F Hazardous Event Quantification Metricsmentioning

confidence: 99%

Section: F Hazardous Event Quantification Metricsmentioning

confidence: 99%

Section: F Hazardous Event Quantification Metricsmentioning

confidence: 99%

See 2 more Smart Citations

Review of Graph-Based Hazardous Event Detection Methods for Autonomous Driving Systems

Xiao

Dianati

Geiger

et al. 2023

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

show abstract

“…and topography (e.g., side slopes, inclines), the control and navigation of mobile robots is a difficult challenge in outdoor environments [23], [71]. The fact that the WTI can create safety issues for mobile robots, highlights the importance of considering this interaction when designing a trajectory tracking or navigation system in outdoor environments.…”

Section: Impact Of Outdoor Environment On Motion Controlmentioning

confidence: 99%

Trajectory Tracking of Mobile Robots with Slip and Skid Compensation

Nori Zadeh

View full text Add to dashboard Cite

Autonomous wheeled mobile robots are capable of working in outdoor environments to reduce the risk for human operators or increase productivity. Accounting for wheel-terrain interaction is crucial for the navigation and traction control of mobile robots in outdoor environments and rough terrains. Wheel-terrain interaction could affect the dynamics and controllability of the robot, which could cause slipping, skidding or loss of mechanical stability. In order to reduce risks related to wheel-terrain interaction, the effects of this interaction should be considered when designing the navigation system. However, the robot could experience different unanticipated surface types and terrain conditions while traversing in outdoor environments, which makes it hard or almost impossible to pre-model every significant detail. Hence, an online adaptive method is needed to capture wheel-terrain interaction effects on the robot’s behaviour in outdoor environments. The capacity of solving highly nonlinear problems has made artificial intelligence a common approach to be able to utilize and adapt robots to different situations in outdoor environments. Wheel slip is one of the surface hazards that need to be detected to mitigate the risk of losing the robot’s controllability or mission failure occurring. Despite prior research in this area, the open problems are (1) the need for in situ slip estimation in harsh environments using low-cost/power and easy to integrate sensors, and (2) removing the need for prior information about the soil, as this is not always available. This thesis addresses these open problems and presents a novel slip estimation method that utilizes only two proprioceptive sensors (IMU and wheel encoder) to estimate the slippage at the vehicle-level using deep learning methods. It is experimentally shown to be real-world feasible in outdoor, uneven terrains without prior soil information assumptions. Comparison with previously used machine learning algorithms for continuous and discrete slip estimation problems show more than 9% and 14% improvement in estimation performance respectively.Skidding is another surface hazard for mobile robots’ navigation and traction control systems operating in outdoor environments and rough terrains due to the wheel-terrain interaction. It could lead to high trajectory tracking errors, losing the robot’s controllability, and mission failure occurring. As was the case for the slip estimation problem, despite research in this field, the development of a real-world feasible in situ skid estimation system with the capability of operating in harsh and unforeseen environments using low-cost/power and easy to integrate sensors is still an open problem in terramechanics. This thesis presents a novel velocity-based definition and a real-world feasible in situ estimation for the mobile robot’s undesired skidding at the vehicle-level in outdoor environments. The proposed technique estimates the undesired skidding using a combination of two proprioceptive sensors (e.g., IMU and wheel encoder) and deep learning to address the open problem in this domain. The practicality of a velocity-based definition and the performance of the proposed undesired skid estimation technique are evaluated experimentally. The results show that the proposed technique performs with less than 11.79 mm/sec mean absolute error and estimates the direction of undesired skidding with approximately 98% accuracy.The final contribution of this work is to design a robust trajectory tracking system with both slip and skid compensation at the vehicle-level for outdoor environments. In addition to the general slipping and skidding hazards for mobile robots in outdoor environments, slip and skid cause uncertainty for the trajectory tracking system and put the validity of stability analysis at risk. Despite research in this field, having a real-world feasible online slip and skid compensator for outdoor and harsh environments is still an open problem. This thesis presents a novel trajectory tracking technique with real-world feasible online slip and skid compensation at the vehicle-level for skid-steering mobile robots in outdoor environments. Dealing with slip and skid at the vehicle-level has the advantage of only requiring two parameters rather than the conventional three slip and skid parameters at the wheel-level. The sliding-mode control is utilized as the trajectory tracking technique to steer the robot based on the robot’s kinematics and dynamics model. The developed deep learning models are integrated into the control-feedback loop to estimate the robot’s slipping and skidding and feed the compensator in a real-time manner. The experimental results show that the proposed controller with the slip and skid compensator improves the performance of the trajectory tracking system by more than 27%.

show abstract

Autonomous Off-Road Navigation Using Near-Feature-Based World Knowledge Incorporation on the Example of Forest Path Detection

Wolf

Vierling

Ropertz

et al. 2022

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

Combining Onthologies and Behavior-based Control for Aware Navigation in Challenging Off-road Environments

Cited by 5 publications

References 0 publications

Review of Graph-Based Hazardous Event Detection Methods for Autonomous Driving Systems

Review of Graph-Based Hazardous Event Detection Methods for Autonomous Driving Systems

Trajectory Tracking of Mobile Robots with Slip and Skid Compensation

Autonomous Off-Road Navigation Using Near-Feature-Based World Knowledge Incorporation on the Example of Forest Path Detection

Contact Info

Product

Resources

About