Unfreezing the robot: Navigation in dense, interacting crowds

Trautman, Peter; Krause, Andreas

doi:10.1109/iros.2010.5654369

Cited by 516 publications

(444 citation statements)

References 14 publications

Supporting

Mentioning

441

Contrasting

Unclassified

Order By: Relevance

“…Trautman and Krause (2010) use GPs to model interactions between the agent and dynamic obstacles present in the environment. Althoff et al (2011) use Monte Carlo sampling to estimate inevitable collision states probabilistically, while Henry et al (2010) apply inverse reinforcement learning for human-like behavior.…”

Section: Related Workmentioning

confidence: 99%

“…However, if this assumption is broken, the agent may be unable to find a path at all, and will come to a stop. This "frozen robot" behavior (Trautman and Krause (2010)) actually puts the agent at added risk in a dynamic environment. This is particularly likely to occur in heavily constrained environments for large values of p safe , as is the case here.…”

Section: Complex Scenariomentioning

confidence: 99%

See 1 more Smart Citation

Probabilistically safe motion planning to avoid dynamic obstacles with uncertain motion patterns

et al. 2013

View full text Add to dashboard Cite

This paper presents a real-time path planning algorithm that guarantees probabilistic feasibility for autonomous robots with uncertain dynamics operating amidst one or more dynamic obstacles with uncertain motion patterns. Planning safe trajectories under such conditions requires both accurate prediction and proper integration of future obstacle behavior within the planner. Given that available observation data is limited, the motion model must provide generalizable predictions that satisfy dynamic and environmental constraints, a limitation of existing approaches. This work presents a novel solution, named RR-GP, which builds a learned motion pattern model by combining the flexibility of Gaussian processes (GP) with the efficiency of RRT-Reach, a sampling-based reachability computation. Obstacle trajectory GP predictions are conditioned on dynamically feasible paths identified from the reachability analysis, yielding more accurate predictions of future behavior. RR-GP predictions are integrated with a robust path planner, using chance-constrained RRT, to identify probabilistically feasible paths. Theoretical guarantees of probabilistic feasibility are shown for linear systems under Gaussian uncertainty; approximations for nonlinear dynamics and/or non-Gaussian uncertainty are also presented. Simulations demonstrate that, with this planner, an autonomous vehicle can safely navigate a complex environment in realtime while significantly reducing the risk of collisions with dynamic obstacles.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Complex Scenariomentioning

confidence: 99%

Probabilistically safe motion planning to avoid dynamic obstacles with uncertain motion patterns

et al. 2013

View full text Add to dashboard Cite

show abstract

“…Trautman and Krause [26] point out that joint collision avoidance is crucial for mobile robot navigation to prevent the robot from "freezing" and getting stuck in densely populated environments. Their work assumes humans to be utilityoptimizing agents that prefer trajectories with low cost.…”

Section: Related Workmentioning

confidence: 99%

“…To tackle the optimization problem, the authors propose sampling from a joint density function, whereas we exploit the topological structure of the problem. Furthermore, as opposed to Trautman and Krause [26], we learn our model from observations of pedestrians to achieve more natural and human-like trajectories.…”

Section: Related Workmentioning

confidence: 99%

Feature-Based Prediction of Trajectories for Socially Compliant Navigation

Kuderer

Kretzschmar

Sprunk

et al. 2012

Robotics: Science and Systems VIII

191

184

View full text Add to dashboard Cite

Abstract-Mobile robots that operate in a shared environment with humans need the ability to predict the movements of people to better plan their navigation actions. In this paper, we present a novel approach to predict the movements of pedestrians. Our method reasons about entire trajectories that arise from interactions between people in navigation tasks. It applies a maximum entropy learning method based on features that capture relevant aspects of the trajectories to determine the probability distribution that underlies human navigation behavior. Hence, our approach can be used by mobile robots to predict forthcoming interactions with pedestrians and thus react in a socially compliant way. In extensive experiments, we evaluate the capability and accuracy of our approach and demonstrate that our algorithm outperforms the popular social forces method, a state-of-the-art approach. Furthermore, we show how our algorithm can be used for autonomous robot navigation using a real robot.

show abstract

“…As we have argued in the introduction, a local planner should be able to navigate the robot safely and reliably through a normal room that contains no navigation traps; navigation between rooms would definitely need a planner. In the field of human-aware navigation, local planning has mostly focused on how to predict the movement of people and thus ensure their safety [1,21]. In this paper, we have not even included a person, but even in static environments an observer should be able to anticipate and appreciate a robot's movements.…”

Section: Related Workmentioning

confidence: 99%

Heuristic Decision-Making for Human-aware Navigation in Domestic Environments

Kirsch¹

EPiC Series in Computing

View full text Add to dashboard Cite

show abstract

Unfreezing the robot: Navigation in dense, interacting crowds

Cited by 516 publications

References 14 publications

Probabilistically safe motion planning to avoid dynamic obstacles with uncertain motion patterns

Probabilistically safe motion planning to avoid dynamic obstacles with uncertain motion patterns

Feature-Based Prediction of Trajectories for Socially Compliant Navigation

Heuristic Decision-Making for Human-aware Navigation in Domestic Environments

Contact Info

Product

Resources

About