Reciprocal n-Body Collision Avoidance
Citations
547 citations
Cites background or result from "Reciprocal n-Body Collision Avoidan..."
...We additionally remark that the illustration in Figure 2(b), the crowd experiments catalogued in the research of [8], [9], [7], the multi-robot coordination theorems of [26], [25], and the tracking experiments of [18], [19], [16], all corroborate the argument that autonomous dynamic agents utilize joint collision avoidance behaviors for successful crowd navigation....
[...]
...([26], [25]), show that robots programmed to jointly avoid each other are guaranteed to be collision free and show improved efficiency at joint navigation tasks....
[...]
515 citations
Cites methods from "Reciprocal n-Body Collision Avoidan..."
...[left-handed / right-handed] agents [Avg / 75th / 90th pctl] [10th pctl / avg] passing crossing overtaking 2 ORCA [6] 0.46 / 0.49 / 0.82 0.108 / 0.131 45 / 55 51 / 49 50 / 50 CADRL [14] 0.25 / 0.30 / 0.47 0.153 / 0.189 37 / 63 38 / 62 43 / 57 SA-CADRL(none) 0.27 / 0.28 / 0.54 0.169 / 0.189 10 / 90 32 / 68 63 / 37 SA-CADRL(lh) 0.30 / 0.36 / 0.67 0.163 / 0.192 98 / 2 85 / 15 86 / 14 SA-CADRL(rh) 0.31 / 0.38 / 0.69 0.168 / 0.199 2 / 98 15 / 85 17 / 83 4 ORCA [6] 0.86 / 1.14 / 1.80 0.106 / 0.125 46 / 54 50 / 50 48 / 52 CADRL(minimax) [14] 0.41 / 0.54 / 0.76 0.096 / 0.173 31 / 69 41 / 59 46 / 54 SA-CADRL(none) 0.44 / 0.63 / 0.85 0.162 / 0.183 33 / 67 33 / 67 62 / 38 SA-CADRL(lh) 0.49 / 0.69 / 1.00 0.155 / 0.178 83 / 17 67 / 33 73 / 27 SA-CADRL(rh) 0.46 / 1.63 / 1.02 0.155 / 0.180 12 / 88 29 / 71 30 / 70 (a) passing on the right (b) overtaking on the left Fig....
[...]
...On the two-agent test-set, all RL-based methods produced more time-efficient paths than ORCA3....
[...]
...The four-agent SA-CADRL (none) policy, in comparison, exhibited a stronger preference than ORCA and CADRL in each of the passing, crossing, and overtaking scenarios (third row in Table I)....
[...]
...Similarly, the bottom rows of Table I show that in the fouragent test set, all RL-based methods outperformed ORCA, and SA-CADRL (lh/rh) exhibited behaviors that respect the social norms....
[...]
...Evidently, the optimal reciprocal collision avoidance (ORCA) [6] algorithm – a reactive, rule-based method that computes a velocity vector based on an agent’s joint geometry with its neighbors – attains nearly 50-50 left/right-handedness on these test sets (first row of Table I)....
[...]
429 citations
420 citations
Cites background or methods from "Reciprocal n-Body Collision Avoidan..."
...To achieve more human-like behavior, Guy et al. (2010) extended RVO by introducing response and observation time to other agents....
[...]
...Such methods include the dynamic window approach by Fox et al. (1997), the velocity obstacles by Fiorini and Shillert (1998) as well as its extension to multiple obstacles, the reciprocal velocity obstacles (RVO) (van den Berg et al., 2009)....
[...]
...To optimize the parameters of the social forces method and RVO, we minimized the norm of the discrepancy between the feature values as induced by the methods and the empirical feature values using stochastic gradient descend....
[...]
...We compared our approach to the approach of Kuderer et al. (2012), the social forces algorithm by Helbing and Molnar (1995), and the RVO introduced by van den Berg et al. (2009)....
[...]
...Similarly, van den Berg et al. (2009) presented an approach to reciprocal collision avoidance that allows a set of mobile robots to navigate without collisions....
[...]
390 citations
References
7,365 citations
6,515 citations
6,340 citations
"Reciprocal n-Body Collision Avoidan..." refers background in this paper
...1 Note that the problem of (local) collision-avoidance differs from motion planning, where the global environment of the robot is considered to be known and a complete path towards a goal configuration is planned at once [18], and collision detection, which simply determines if two geometric objects intersect or not (see e....
[...]
4,805 citations