Probabilistic mapping of dynamic obstacles using Markov chains for replanning in dynamic environments

Rohrmüller, Florian; Althoff, Matthias; Wollherr, Dirk; Buss, Martin

doi:10.1109/iros.2008.4650952

Cited by 38 publications

(33 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…By including more information, e.g., (i) obstacles are not adversary and will try to avoid collisions, (ii) certain obstacles such as humans may move away over time and (iii) there are no flying obstacles, these assumptions can be relaxed to result in more efficient robot navigation. The representation can be improved by adding explicit obstacle models of, e.g., humans as proposed in Philippsen et al (2006), Philippsen et al (2008) and Rohrmüller et al (2008), but also of static parts of the environment, e.g., walls. By discriminating in obstacle representations, the probability of their presence can be modeled separately and thus more accurately.…”

Section: Discussionmentioning

confidence: 99%

“…Finally, some approaches explicitly model the uncertainty that arises due to unpredictable moving obstacles, e.g., humans (Philippsen et al 2006(Philippsen et al , 2008Rohrmüller et al 2008). Moving obstacles are extracted from subsequent sensor readings and their position and velocity is estimated to obtain a probabilistic model that resembles the risk of collision.…”

Section: Related Work and Contributionmentioning

confidence: 99%

“…12a). Associating this data with people tracked using, e.g., a laser rangefinder as is done in Rohrmüller et al (2008) could prevent these issues.…”

Section: Experiences In a Real World Experimentsmentioning

confidence: 99%

See 2 more Smart Citations

A representation method based on the probability of collision for safe robot navigation in domestic environments

2017

View full text Add to dashboard Cite

This paper introduces a three-dimensional volumetric representation for safe navigation. It is based on the OctoMap representation framework that probabilistically fuses sensor measurements to represent the occupancy probability of volumes. To achieve safe navigation in a domestic environment this representation is extended with a model of the occupancy probability if no sensor measurements are received, and a proactive approach to deal with unpredictably moving obstacles that can arise from behind occlusions by always expecting obstacles to appear on the robot's path. By combining the occupancy probability of volumes with the position uncertainty of the robot, a probability of collision is obtained. It is shown that by relating this probability to a safe velocity limit a robot in a real domestic environment can move close to a certain maximum velocity but decides to attain a slower safe velocity limit when it must, analogous to slowing down in traffic when approaching an occluded intersection.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Work and Contributionmentioning

confidence: 99%

See 1 more Smart Citation

A representation method based on the probability of collision for safe robot navigation in domestic environments

2017

View full text Add to dashboard Cite

show abstract

“…Koppula and Saxena [23] anticipate high-level movement using a temporal conditional random field. Markov chains are used to model human dynamics in [24], and probabilistic reachability analysis, based on the dynamics obtained, is used in a collision avoidance algorithm. Ding et al [25] present another probabilistic prediction of the human occupancy using a hidden Markov model (HMM).…”

Section: B Probabilistic Motion Predictionmentioning

confidence: 99%

Overapproximative Human Arm Occupancy Prediction for Collision Avoidance

Pereira

Althoff

2018

IEEE Trans. Automat. Sci. Eng.

View full text Add to dashboard Cite

Abstract-Predicting the occupancy of a human in real time is of great interest in human-robot coexistence for obtaining regions that a robot should avoid in safe motion planning. The human body is composed of joints and links, suiting approximation by a kinematic chain, but the control strategy of the human is completely unknown, meaning the potential occupancy grows very fast and it is difficult to compute tightly in real time. As such, most previous work considers only specific, known, or probable movements, and usually does not account for a range of human dimensions. Focusing on the human arm, we analyze archetypal movements performed by test subjects to create a dynamic model. Motion-capture data of subjects are fitted, for modeling purposes, to two abstractions: a 4-degree of freedom (DOF) model and a 3-DOF model, to obtain dynamic parameters. We validate our approach on movements from a publicly available database. The prediction is shown to be computationally fast, and reachable sets of the abstraction are shown to enclose all possible future occupancies of the arm for different subjects, tightly but overapproximatively. The 3-DOF model has advantages over the 4-DOF in terms of speed, though the 4-DOF model is tighter at smaller time horizons. Such an overapproximative representation is intended for certifiable safety-guaranteed collision avoidance algorithms for robots.Note to Practitioners-Motivated by the need to keep humans safe when working alongside robots, our earlier work proposes a method of trajectory planning where the robot certifies each movement as safe before it performs it. For this to prove that unsafe collisions cannot occur, an overapproximative prediction of the human is needed, meaning that no possible future position of the human is outside the predicted region, or reachable occupancy. However, making this prediction both small enough (so that it does not include unreachable regions) and fast enough for real-time use is not straightforward. We find the limits of human motion by asking a range of test subjects to perform movements as fast as possible. We calculate the reachable occupancies based on these limits and show that our predictions are indeed overapproximative, fast, and not wasteful of volume. One can then use the aforementioned approach to guarantee safety; future challenges are reliably sensing the human's pose and implementing our approach on an industrial robot.

show abstract

“…Among others, Hidden Markov Models [6] and Markov chains [7] can be used to find probable movements and then calculate the most likely occupancy accordingly [8]. Though these methods work well for most human behaviour, unusual movements like reflex movements, tripping, or grabbing falling objects, may not occur in the training data and may not be accounted for.…”

Section: A Human Motion Predictionmentioning

confidence: 99%

Reachset Conformance Testing of Human Arms with a Biomechanical Model

Stark¹,

Pereira²,

Althoff³

2018

2018 Second IEEE International Conference on Robotic Computing (IRC)

View full text Add to dashboard Cite

Abstract-Guaranteeing safety in human-robot co-existence often requires a prediction of the volume that could be occupied by the human up to a future time, in order to avoid collisions. Such predictions should be simple and fast for real-time calculation and collision-checking, but account even for unexpected movement. We use a complex biomechanical model to search for extreme human movement, to validate such a prediction. Since the model has a large input space and highly nonlinear dynamics, we use an exploration algorithm based on RRTs to efficiently find the extreme movements. We find that the simple prediction encloses all arm positions found by the exploration algorithm, except where the biomechanical model does not account for collision between body tissue.

show abstract

Probabilistic mapping of dynamic obstacles using Markov chains for replanning in dynamic environments

Cited by 38 publications

References 23 publications

A representation method based on the probability of collision for safe robot navigation in domestic environments

A representation method based on the probability of collision for safe robot navigation in domestic environments

Overapproximative Human Arm Occupancy Prediction for Collision Avoidance

Reachset Conformance Testing of Human Arms with a Biomechanical Model

Contact Info

Product

Resources

About